third Push

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: ml-agents
 tags:
-- Pyramids
+- SnowballTarget
 - deep-reinforcement-learning
 - reinforcement-learning
-- ML-Agents-Pyramids
+- ML-Agents-SnowballTarget
 ---
 
-  # **ppo** Agent playing **Pyramids**
-  This is a trained model of a **ppo** agent playing **Pyramids**
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget**
   using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
 
   ## Usage (with ML-Agents)

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5fbc54e5d7e75529bfd224180fb5e78bfe2982344a9705f6bf6ff1aea717635
-size 649740
+oid sha256:5569d6914571bb00196f565b2d63ce5038976cc0dd52109778b5caf4cbc77c0e
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4d9f9ea36bcd3ac4c2e0c7f62325bb6f36be0b715d4d7f129ed63a88aa6ee8
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb312975bcbfa7fe61abbb2716af9ca8303aa4ddbb7c35fb315ef0dde2a608b
+size 3850564

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5569d6914571bb00196f565b2d63ce5038976cc0dd52109778b5caf4cbc77c0e
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a6118b325f892a29351cbdf88376ab80922cfc5c0ba08926ab23becb8264f8
+size 3850564

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5569d6914571bb00196f565b2d63ce5038976cc0dd52109778b5caf4cbc77c0e
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd159eb1815034e112f5309f43a19784c4da96606b8d893637216d2521f4378d
+size 3850564

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c31649cb974c7b80ce7d8b8ab9db4b88d0ee6e29f31d5b85f03eb5b9e7b2df23
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed372851350db4b3286c53d92f205d18de37c0132029d3423f91f94eec884c3e
+size 3850487

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c437161641adcef96f04cffc585a0956770c640b33e8b006e637b1eded501d
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6278a9312b7e8f0e3625be4baffd2b49cecc59e3791b8990dd74a5564e21f69c
+size 3850487

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769966567fbba24c8158845a2b7beb7696ad6275cec14c7429c14ff2158f9a5f
-size 1286389
+oid sha256:635dbcd3588dbafe65744fb07939c7707f7113e891f59f98e7edc7c44e27970a
+size 3849717

SnowballTarget/events.out.tfevents.1765730724.761ef42fcc36.8075.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1e027c1c5f8c52617123088e7a9133e5a850fad7387a7fde744039a0e98887
+size 23411

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget3", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -1,12 +1,12 @@
 default_settings: null
 behaviors:
-  Pyramids:
+  SnowballTarget:
     trainer_type: ppo
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.01
+      beta: 0.005
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -14,10 +14,10 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 500000
+    checkpoint_interval: 50000
     network_settings:
       normalize: false
-      hidden_units: 512
+      hidden_units: 256
       num_layers: 2
       vis_encode_type: simple
       memory: null
@@ -35,30 +35,17 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-      rnd:
-        gamma: 0.99
-        strength: 0.01
-        network_settings:
-          normalize: false
-          hidden_units: 64
-          num_layers: 3
-          vis_encode_type: simple
-          memory: null
-          goal_conditioning_type: hyper
-          deterministic: false
-        learning_rate: 0.0001
-        encoding_size: null
     init_path: null
-    keep_checkpoints: 5
+    keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 3000000
-    time_horizon: 128
-    summary_freq: 30000
+    max_steps: 200000
+    time_horizon: 64
+    summary_freq: 10000
     threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -79,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: SnowballTarget3
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,14 +1,9 @@
-Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
-Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
-Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55073 [Flags] 2 [Guid] 2233890928 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
-Initialize engine version: 2021.3.5f1 (40eb3a945986)
-[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -36,31 +31,10 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.089 seconds
+- Completed reload, in  0.082 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
-WARNING: Shader Did you use #pragma only_renderers and omit this platform?
-WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
@@ -68,90 +42,85 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.742951 ms
+UnloadTime: 0.688478 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
-PlayerConnection::CleanupMemory Statistics:
+Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
-    [ALLOC_TEMP_AUDIO_FMOD stream thread]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 5234 frames, [32.0 KB-64.0 KB]: 34163 frames, [64.0 KB-128.0 KB]: 16866 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
       Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 198 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 10]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 6]
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AUDIO_FMOD mixer thread]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 1]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Background Job.Worker 6]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 3]
+    [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_BatchDeleteObjects]
+    [ALLOC_TEMP_EnlightenWorker]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 1]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Loading.PreloadManager]
-      Initial Block Size 256.0 KB
-      Current Block Size 320.0 KB
-      Peak Allocated Bytes 251.5 KB
-      Overflow Count 4
-    [ALLOC_TEMP_Profiler.Dispatcher]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 12]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -171,64 +140,48 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 0]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 4]
+    [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker]
+    [ALLOC_TEMP_BatchDeleteObjects]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Loading.AsyncRead]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 128 B
-      Overflow Count 0
-[ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55965 frames
-  Requested Block Size 1.0 MB
-  Peak Block count 2
-  Peak Allocated memory 1.6 MB
-  Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12723
+  Peak main deferred allocation count 44
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56262 frames, [32.0 MB-64.0 MB]: 1 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 32.4 MB
+      Peak Block count 1
+      Peak Allocated memory 7.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 56264 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.7 MB
+      Peak Allocated memory 17.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,63 +208,52 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 56263 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4410 frames, [64.0 KB-128.0 KB]: 1048 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.0 KB
+      Peak Allocated memory 67.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 56264 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.7 KB
+      Peak Allocated memory 39.6 KB
       Peak Large allocation bytes 0 B
 [ALLOC_CACHEOBJECTS] Dual Thread Allocator
-  Peak main deferred allocation count 1
+  Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55965 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.4 MB
+      Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 56263 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
-      Peak Allocated memory 4.7 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 56264 frames
+      Peak usage frame count: [0-1.0 KB]: 5458 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 56264 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.9 KB
+      Peak Allocated memory 1.7 KB
       Peak Large allocation bytes 0 B
-[ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 56264 frames
-  Requested Block Size 16.0 MB
-  Peak Block count 1
-  Peak Allocated memory 29.2 KB
-  Peak Large allocation bytes 0 B
-    [ALLOC_PROFILER_BUCKET]
-      Large Block size 4.0 MB
-      Used Block count 1
-      Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1765739089677,"processId":11866,"allocatedMemory":1970545,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":11015},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -1,250 +1,214 @@
 {
     "name": "root",
     "gauges": {
-        "Pyramids.Policy.Entropy.mean": {
-            "value": 0.14274290204048157,
-            "min": 0.1400885283946991,
-            "max": 1.4381762742996216,
-            "count": 100
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.8074185848236084,
+            "min": 0.8050537109375,
+            "max": 2.8650498390197754,
+            "count": 20
         },
-        "Pyramids.Policy.Entropy.sum": {
-            "value": 4232.04150390625,
-            "min": 4200.41455078125,
-            "max": 43628.515625,
-            "count": 100
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7673.7060546875,
+            "min": 7673.7060546875,
+            "max": 29246.4296875,
+            "count": 20
         },
-        "Pyramids.Step.mean": {
-            "value": 2999943.0,
-            "min": 29952.0,
-            "max": 2999943.0,
-            "count": 100
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
         },
-        "Pyramids.Step.sum": {
-            "value": 2999943.0,
-            "min": 29952.0,
-            "max": 2999943.0,
-            "count": 100
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
         },
-        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7661646604537964,
-            "min": -0.1306808739900589,
-            "max": 0.9027830958366394,
-            "count": 100
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.020735740661621,
+            "min": 0.351095050573349,
+            "max": 13.020735740661621,
+            "count": 20
         },
-        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 222.18775939941406,
-            "min": -30.97136878967285,
-            "max": 272.6405029296875,
-            "count": 100
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2539.04345703125,
+            "min": 68.11244201660156,
+            "max": 2637.59814453125,
+            "count": 20
         },
-        "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.018598448485136032,
-            "min": -0.0064407638274133205,
-            "max": 0.5080781579017639,
-            "count": 100
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06621911934980387,
+            "min": 0.06138560041196315,
+            "max": 0.07300320537544001,
+            "count": 20
         },
-        "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 5.393549919128418,
-            "min": -1.867821455001831,
-            "max": 120.41452026367188,
-            "count": 100
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2648764773992155,
+            "min": 0.24801534933652092,
+            "max": 0.35674936726960976,
+            "count": 20
         },
-        "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06921964839080622,
-            "min": 0.06456119794295066,
-            "max": 0.073816837427837,
-            "count": 100
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18595149375352205,
+            "min": 0.12106652085797168,
+            "max": 0.28993210094232186,
+            "count": 20
         },
-        "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.969075077471287,
-            "min": 0.5085131924558597,
-            "max": 1.0738666915179542,
-            "count": 100
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7438059750140882,
+            "min": 0.4842660834318867,
+            "max": 1.3410455529011933,
+            "count": 20
         },
-        "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01288479595555642,
-            "min": 0.0006376268148680634,
-            "max": 0.016289365808026764,
-            "count": 100
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
         },
-        "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.18038714337778988,
-            "min": 0.008289148593284824,
-            "max": 0.24434048712040146,
-            "count": 100
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
         },
-        "Pyramids.Policy.LearningRate.mean": {
-            "value": 1.5567423382619082e-06,
-            "min": 1.5567423382619082e-06,
-            "max": 0.00029838354339596195,
-            "count": 100
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19729400000000002,
+            "count": 20
         },
-        "Pyramids.Policy.LearningRate.sum": {
-            "value": 2.1794392735666716e-05,
-            "min": 2.1794392735666716e-05,
-            "max": 0.0041173670275443655,
-            "count": 100
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
         },
-        "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10051888095238097,
-            "min": 0.10051888095238097,
-            "max": 0.19946118095238097,
-            "count": 100
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048649706,
+            "count": 20
         },
-        "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4072643333333337,
-            "min": 1.3962282666666668,
-            "max": 2.8724556333333333,
-            "count": 100
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
+            "max": 0.023089828,
+            "count": 20
         },
-        "Pyramids.Policy.Beta.mean": {
-            "value": 6.183620714285727e-05,
-            "min": 6.183620714285727e-05,
-            "max": 0.009946171977142856,
-            "count": 100
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
         },
-        "Pyramids.Policy.Beta.sum": {
-            "value": 0.0008657069000000018,
-            "min": 0.0008657069000000018,
-            "max": 0.13725831777,
-            "count": 100
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
         },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.006470296997576952,
-            "min": 0.006384584587067366,
-            "max": 0.5330579876899719,
-            "count": 100
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.454545454545453,
+            "min": 3.4318181818181817,
+            "max": 25.527272727272727,
+            "count": 20
         },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.0905841588973999,
-            "min": 0.08938418328762054,
-            "max": 3.7314059734344482,
-            "count": 100
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1120.0,
+            "min": 151.0,
+            "max": 1404.0,
+            "count": 20
         },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 238.624,
-            "min": 207.54225352112675,
-            "max": 999.0,
-            "count": 100
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.454545454545453,
+            "min": 3.4318181818181817,
+            "max": 25.527272727272727,
+            "count": 20
         },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29828.0,
-            "min": 15984.0,
-            "max": 32862.0,
-            "count": 100
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1120.0,
+            "min": 151.0,
+            "max": 1404.0,
+            "count": 20
         },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7133615875840187,
-            "min": -1.0000000521540642,
-            "max": 1.7912214125905719,
-            "count": 100
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 214.17019844800234,
-            "min": -30.369201704859734,
-            "max": 255.76799814403057,
-            "count": 100
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7133615875840187,
-            "min": -1.0000000521540642,
-            "max": 1.7912214125905719,
-            "count": 100
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 214.17019844800234,
-            "min": -30.369201704859734,
-            "max": 255.76799814403057,
-            "count": 100
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.016131126304913777,
-            "min": 0.014041643471843428,
-            "max": 12.411121679469943,
-            "count": 100
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 2.0163907881142222,
-            "min": 1.937746799114393,
-            "max": 198.5779468715191,
-            "count": 100
-        },
-        "Pyramids.IsTraining.mean": {
+        "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 20
         },
-        "Pyramids.IsTraining.sum": {
+        "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1765731620",
+        "start_time_seconds": "1765730724",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1765739089"
+        "end_time_seconds": "1765731164"
     },
-    "total": 7468.946267567,
+    "total": 440.9279657400002,
     "count": 1,
-    "self": 0.46490740700028255,
+    "self": 0.4298456240003361,
     "children": {
         "run_training.setup": {
-            "total": 0.02324181999983921,
+            "total": 0.023854558000039106,
             "count": 1,
-            "self": 0.02324181999983921
+            "self": 0.023854558000039106
         },
         "TrainerController.start_learning": {
-            "total": 7468.4581183400005,
+            "total": 440.47426555799984,
             "count": 1,
-            "self": 4.5424503695903695,
+            "self": 0.4048057149802844,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.133333829000094,
+                    "total": 1.9756916989999809,
                     "count": 1,
-                    "self": 2.133333829000094
+                    "self": 1.9756916989999809
                 },
                 "TrainerController.advance": {
-                    "total": 7461.7061809874085,
-                    "count": 195532,
-                    "self": 4.5259385993731485,
+                    "total": 438.01683964601943,
+                    "count": 18192,
+                    "self": 0.3822870770050031,
                     "children": {
                         "env_step": {
-                            "total": 5445.430207719206,
-                            "count": 195532,
-                            "self": 4983.937026356094,
+                            "total": 318.8410042340163,
+                            "count": 18192,
+                            "self": 249.85267042902683,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 458.7629061873022,
-                                    "count": 195532,
-                                    "self": 14.206423121025637,
+                                    "total": 68.7580491260037,
+                                    "count": 18192,
+                                    "self": 1.258827515003759,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 444.55648306627654,
-                                            "count": 187546,
-                                            "self": 444.55648306627654
+                                            "total": 67.49922161099994,
+                                            "count": 18192,
+                                            "self": 67.49922161099994
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.7302751758097656,
-                                    "count": 195532,
+                                    "total": 0.230284678985754,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 7448.365369912906,
-                                            "count": 195532,
+                                            "total": 438.703580552017,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 2829.2585284005963,
+                                            "self": 219.1982010950419,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002758853999694111,
+                                                            "total": 0.0021242299999357783,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008029660007196071,
+                                                            "self": 0.0005943430005572736,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0019558879989745037,
-                                                                    "count": 8,
+                                                                    "total": 0.0015298869993785047,
+                                                                    "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0019558879989745037
+                                                                    "self": 0.0015298869993785047
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.055401129000074434,
+                                                            "total": 0.03531760700002451,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005702510002265626,
+                                                            "self": 0.0005521509999653063,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005441789999167668,
+                                                                    "total": 0.00040437300003759447,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005441789999167668
+                                                                    "self": 0.00040437300003759447
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0525886319996971,
+                                                                    "total": 0.031836515999884796,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0525886319996971
+                                                                    "self": 0.031836515999884796
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016980670002340048,
+                                                                    "total": 0.0025245670001368126,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00037161000045671244,
+                                                                    "self": 0.00036889600050926674,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013264569997772924,
-                                                                            "count": 8,
+                                                                            "total": 0.002155670999627546,
+                                                                            "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013264569997772924
+                                                                            "self": 0.002155670999627546
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 4619.10684151231,
-                                                    "count": 195531,
+                                                    "total": 219.5053794569751,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 103.07891526709591,
+                                                    "self": 10.086080039985745,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 68.12664852603984,
-                                                            "count": 195531,
+                                                            "total": 5.455175400003782,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 68.12664852603984
+                                                            "self": 5.455175400003782
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 4129.806436986028,
-                                                            "count": 195531,
+                                                            "total": 168.32038442400471,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 4129.806436986028
+                                                            "self": 168.32038442400471
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 318.09484073314616,
-                                                            "count": 195531,
+                                                            "total": 35.643739592980864,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 67.98263217252634,
+                                                            "self": 6.631359566016272,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 250.11220856061982,
-                                                                    "count": 1564248,
+                                                                    "total": 29.012380026964593,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 250.11220856061982
+                                                                    "self": 29.012380026964593
                                                                 }
                                                             }
                                                         }
@@ -343,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 2011.7500346688294,
-                            "count": 195532,
-                            "self": 9.43141175385972,
+                            "total": 118.79354833499815,
+                            "count": 18192,
+                            "self": 0.5116992509906595,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 386.2615405150045,
-                                    "count": 195532,
-                                    "self": 385.7353017810028,
+                                    "total": 25.4517417890072,
+                                    "count": 18192,
+                                    "self": 25.027620462007235,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.5262387340017085,
-                                            "count": 6,
-                                            "self": 0.5262387340017085
+                                            "total": 0.4241213269999662,
+                                            "count": 4,
+                                            "self": 0.4241213269999662
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1616.057082399965,
-                                    "count": 1403,
-                                    "self": 895.8630988569594,
+                                    "total": 92.83010729500029,
+                                    "count": 90,
+                                    "self": 37.77675017000411,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 720.1939835430057,
-                                            "count": 68361,
-                                            "self": 720.1939835430057
+                                            "total": 55.05335712499618,
+                                            "count": 4587,
+                                            "self": 55.05335712499618
                                         }
                                     }
                                 }
@@ -376,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.620008884463459e-07,
+                    "total": 9.710001904750243e-07,
                     "count": 1,
-                    "self": 8.620008884463459e-07
+                    "self": 9.710001904750243e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07615229200018803,
+                    "total": 0.07692752699995253,
                     "count": 1,
-                    "self": 0.0009459150005568517,
+                    "self": 0.0006776699997317337,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.07520637699963117,
+                            "total": 0.0762498570002208,
                             "count": 1,
-                            "self": 0.07520637699963117
+                            "self": 0.0762498570002208
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,59 +1,59 @@
 {
-    "Pyramids": {
+    "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 1499976,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499976.onnx",
-                "reward": 1.7886666630705197,
-                "creation_time": 1765735141.6868377,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 17.545454545454547,
+                "creation_time": 1765730835.6153588,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1499976.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
-                "steps": 1999964,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999964.onnx",
-                "reward": 1.6936666866143544,
-                "creation_time": 1765736412.8150268,
+                "steps": 99960,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.545454545454547,
+                "creation_time": 1765730945.9885077,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1999964.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
-                "steps": 2499943,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499943.onnx",
-                "reward": 1.7126666555802028,
-                "creation_time": 1765737740.7316177,
+                "steps": 149984,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 23.727272727272727,
+                "creation_time": 1765731055.4854834,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2499943.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
-                "steps": 2999943,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999943.onnx",
-                "reward": 1.687999991433961,
-                "creation_time": 1765739089.1781359,
+                "steps": 199984,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1765731164.4248745,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2999943.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 3000071,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000071.onnx",
-                "reward": 1.687999991433961,
-                "creation_time": 1765739089.2657182,
+                "steps": 200112,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1765731164.5130486,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-3000071.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 3000071,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.687999991433961,
-            "creation_time": 1765739089.2657182,
+            "steps": 200112,
+            "file_path": "results/SnowballTarget3/SnowballTarget.onnx",
+            "reward": 25.545454545454547,
+            "creation_time": 1765731164.5130486,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-3000071.pt"
+                "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },