First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5b66d3e77b7300672db155264c55ac4473d96b7daf8f79f48e940d81cda5c9
+size 1418184

Pyramids/Pyramids-1000105.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5b66d3e77b7300672db155264c55ac4473d96b7daf8f79f48e940d81cda5c9
+size 1418184

Pyramids/Pyramids-1000105.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac32e60664c18e281cc599cfbcf37ef64287201603762ca0785ad2c566b252f
+size 8650990

Pyramids/Pyramids-499995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8cc3fbbfb23e7907daa2944a78488c814e80085506815d2535f71111ca24cf
+size 1418184

Pyramids/Pyramids-499995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbed905274f38c6cd1ae3809dce7f036aaf7fed958e1875644c1edbe567c50d8
+size 8650990

Pyramids/Pyramids-999977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5b66d3e77b7300672db155264c55ac4473d96b7daf8f79f48e940d81cda5c9
+size 1418184

Pyramids/Pyramids-999977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750e7f7fe59de6ed0bfa420926a8bbdb1b9aa237d61e88c925d9467caf3c174f
+size 8650990

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac32e60664c18e281cc599cfbcf37ef64287201603762ca0785ad2c566b252f
+size 8650990

Pyramids/events.out.tfevents.1688702053.03de92281637.6083.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a59f927edbc55d4e4e11fa6d510aa2ee44c45b5247e25413abc9a6064c655b9
+size 333267

README.md

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

config.json

@@ -1 +1 @@
-{"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": true, "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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "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": {"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": 1000000, "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, "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}, "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}

configuration.yaml

@@ -1,12 +1,12 @@
 default_settings: null
 behaviors:
-  SnowballTarget:
+  Pyramids:
     trainer_type: ppo
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.01
       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: 50000
+    checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 256
+      hidden_units: 512
       num_layers: 2
       vis_encode_type: simple
       memory: null
@@ -35,17 +35,30 @@ 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: 10
+    keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 200000
-    time_horizon: 64
-    summary_freq: 10000
-    threaded: true
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -64,7 +77,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: Pyramids Training
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,14 @@
-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'
+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] 55020 [Flags] 2 [Guid] 1844100840 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+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: 2021.3.14f1 (eee1884e7226)
-[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -34,10 +36,31 @@ ALSA lib pcm.c:2642:(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  0.082 seconds
+- Completed reload, in  0.089 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?
@@ -45,85 +68,90 @@ 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: 0.640085 ms
+UnloadTime: 0.896013 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.
-Memory Statistics:
+PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5370 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3866 frames, [32.0 KB-64.0 KB]: 11499 frames, [64.0 KB-128.0 KB]: 3406 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 9]
+    [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_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]
+    [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 14]
+    [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]
       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_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 12]
+    [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_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_Background Job.Worker 15]
+    [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_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_Background Job.Worker 1]
+    [ALLOC_TEMP_Background Job.Worker 7]
       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 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_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]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -143,48 +171,64 @@ Memory Statistics:
       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 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 3]
+    [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_Background Job.Worker 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 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 4]
+    [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_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_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]: 18473 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 40
+  Peak main deferred allocation count 12451
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18771 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.8 MB
+      Peak Block count 3
+      Peak Allocated memory 29.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18772 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 23.9 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -211,52 +255,63 @@ Memory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4485 frames, [64.0 KB-128.0 KB]: 977 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18771 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.3 KB
+      Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18772 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 39.6 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
 [ALLOC_CACHEOBJECTS] Dual Thread Allocator
-  Peak main deferred allocation count 0
+  Peak main deferred allocation count 1
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18473 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.6 MB
+      Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18771 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 2.2 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 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 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5462 frames
+      Peak usage frame count: [0-1.0 KB]: 18772 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]: 5462 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18772 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.7 KB
+      Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18772 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":1688704470922,"processId":6101,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"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

@@ -1,214 +1,250 @@
 {
     "name": "root",
     "gauges": {
-        "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.8651920557022095,
-            "min": 0.8523612022399902,
-            "max": 2.8740010261535645,
-            "count": 20
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.27957168221473694,
+            "min": 0.27957168221473694,
+            "max": 1.50686776638031,
+            "count": 33
         },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8279.8876953125,
-            "min": 8279.8876953125,
-            "max": 29401.029296875,
-            "count": 20
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 8418.462890625,
+            "min": 8418.462890625,
+            "max": 45712.33984375,
+            "count": 33
         },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.mean": {
+            "value": 989968.0,
+            "min": 29937.0,
+            "max": 989968.0,
+            "count": 33
         },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.sum": {
+            "value": 989968.0,
+            "min": 29937.0,
+            "max": 989968.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.522505760192871,
-            "min": 0.3638897240161896,
-            "max": 12.52877426147461,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.6871842741966248,
+            "min": -0.10674890130758286,
+            "max": 0.6871842741966248,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2441.888671875,
-            "min": 70.5946044921875,
-            "max": 2555.869873046875,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 198.59625244140625,
+            "min": -25.619735717773438,
+            "max": 198.59625244140625,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.0015550628304481506,
+            "min": -0.011162499897181988,
+            "max": 0.5254029631614685,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 0.44941315054893494,
+            "min": -3.0585250854492188,
+            "max": 124.5205078125,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06259346365439734,
-            "min": 0.06255198740380401,
-            "max": 0.07434596892277363,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06431180253599046,
+            "min": 0.0636650842304031,
+            "max": 0.07386721455719882,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2503738546175894,
-            "min": 0.25020794961521603,
-            "max": 0.36708153742844896,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9646770380398568,
+            "min": 0.504679545598411,
+            "max": 1.034877759829054,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.20776893717108985,
-            "min": 0.12567587055530693,
-            "max": 0.3196186223158649,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.01664957369276736,
+            "min": 0.000963503379951944,
+            "max": 0.02907833937842205,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8310757486843594,
-            "min": 0.5027034822212277,
-            "max": 1.5016098129289117,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.24974360539151044,
+            "min": 0.010598537179471384,
+            "max": 0.24974360539151044,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.5116374961533315e-06,
+            "min": 7.5116374961533315e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00011267456244229997,
+            "min": 0.00011267456244229997,
+            "max": 0.003507491030836399,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10250384666666666,
+            "min": 0.10250384666666666,
+            "max": 0.19838354285714285,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.5375577,
+            "min": 1.3886848,
+            "max": 2.569163600000001,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.000260134282,
+            "min": 0.000260134282,
+            "max": 0.00983851593142857,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0039020142299999996,
+            "min": 0.0039020142299999996,
+            "max": 0.11693944364,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.477272727272727,
-            "min": 3.6363636363636362,
-            "max": 24.90909090909091,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.013285608030855656,
+            "min": 0.013285608030855656,
+            "max": 0.6603831052780151,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1077.0,
-            "min": 160.0,
-            "max": 1370.0,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.1992841213941574,
+            "min": 0.19592751562595367,
+            "max": 4.622681617736816,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.477272727272727,
-            "min": 3.6363636363636362,
-            "max": 24.90909090909091,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 270.1862745098039,
+            "min": 270.1862745098039,
+            "max": 999.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1077.0,
-            "min": 160.0,
-            "max": 1370.0,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 27559.0,
+            "min": 16864.0,
+            "max": 32729.0,
+            "count": 33
         },
-        "SnowballTarget.IsTraining.mean": {
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6906543550560775,
+            "min": -0.9999871489501768,
+            "max": 1.6931821223614472,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 174.13739857077599,
+            "min": -30.999601617455482,
+            "max": 189.63639770448208,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6906543550560775,
+            "min": -0.9999871489501768,
+            "max": 1.6931821223614472,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 174.13739857077599,
+            "min": -30.999601617455482,
+            "max": 189.63639770448208,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.037961984457105094,
+            "min": 0.037961984457105094,
+            "max": 14.94113319586305,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.910084399081825,
+            "min": 3.910084399081825,
+            "max": 253.99926432967186,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 33
         },
-        "SnowballTarget.IsTraining.sum": {
+        "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1688700820",
+        "start_time_seconds": "1688702052",
         "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "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",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1688701311"
+        "end_time_seconds": "1688704470"
     },
-    "total": 490.800143774,
+    "total": 2418.717765167,
     "count": 1,
-    "self": 0.4316293919999339,
+    "self": 0.4801527550002902,
     "children": {
         "run_training.setup": {
-            "total": 0.04252697400002603,
+            "total": 0.03893532099982622,
             "count": 1,
-            "self": 0.04252697400002603
+            "self": 0.03893532099982622
         },
         "TrainerController.start_learning": {
-            "total": 490.325987408,
+            "total": 2418.198677091,
             "count": 1,
-            "self": 0.6520620690052965,
+            "self": 1.7420985809471858,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.192583184,
+                    "total": 4.177804108000146,
                     "count": 1,
-                    "self": 4.192583184
+                    "self": 4.177804108000146
                 },
                 "TrainerController.advance": {
-                    "total": 485.33756374199464,
-                    "count": 18204,
-                    "self": 0.3217913209924177,
+                    "total": 2412.185424905052,
+                    "count": 64089,
+                    "self": 1.833884089134699,
                     "children": {
                         "env_step": {
-                            "total": 485.0157724210022,
-                            "count": 18204,
-                            "self": 354.5796261739994,
+                            "total": 1744.6672940279316,
+                            "count": 64089,
+                            "self": 1613.5365879280062,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 130.12360594000555,
-                                    "count": 18204,
-                                    "self": 2.0692647820065133,
+                                    "total": 130.08374863299537,
+                                    "count": 64089,
+                                    "self": 5.254732339032444,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 128.05434115799903,
-                                            "count": 18204,
-                                            "self": 128.05434115799903
+                                            "total": 124.82901629396292,
+                                            "count": 62571,
+                                            "self": 124.82901629396292
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.31254030699730606,
-                                    "count": 18204,
+                                    "total": 1.0469574669300528,
+                                    "count": 64089,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 488.4018560430036,
-                                            "count": 18204,
+                                            "total": 2412.1527199700045,
+                                            "count": 64089,
                                             "is_parallel": true,
-                                            "self": 224.17367479400622,
+                                            "self": 929.8179991549341,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005478624000005539,
+                                                            "total": 0.0019838790001358575,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003760557000020981,
+                                                            "self": 0.0006026540002039837,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0017180669999845577,
-                                                                    "count": 10,
+                                                                    "total": 0.0013812249999318738,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0017180669999845577
+                                                                    "self": 0.0013812249999318738
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04340403500000889,
+                                                            "total": 0.04943509700001414,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00045465100004093983,
+                                                            "self": 0.0005539509998016001,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00032256599999413993,
+                                                                    "total": 0.0005458410000755975,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00032256599999413993
+                                                                    "self": 0.0005458410000755975
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04061275599997316,
+                                                                    "total": 0.046487401000149475,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04061275599997316
+                                                                    "self": 0.046487401000149475
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0020140620000006493,
+                                                                    "total": 0.0018479039999874658,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003402859999823704,
+                                                                    "self": 0.0003614270001435216,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0016737760000182789,
-                                                                            "count": 10,
+                                                                            "total": 0.0014864769998439442,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0016737760000182789
+                                                                            "self": 0.0014864769998439442
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 264.2281812489974,
-                                                    "count": 18203,
+                                                    "total": 1482.3347208150703,
+                                                    "count": 64088,
                                                     "is_parallel": true,
-                                                    "self": 10.932735793989508,
+                                                    "self": 35.36632236811374,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.466403400007152,
-                                                            "count": 18203,
+                                                            "total": 23.262175593977872,
+                                                            "count": 64088,
                                                             "is_parallel": true,
-                                                            "self": 5.466403400007152
+                                                            "self": 23.262175593977872
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 211.65751243200293,
-                                                            "count": 18203,
+                                                            "total": 1316.27704778694,
+                                                            "count": 64088,
                                                             "is_parallel": true,
-                                                            "self": 211.65751243200293
+                                                            "self": 1316.27704778694
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 36.17152962299778,
-                                                            "count": 18203,
+                                                            "total": 107.42917506603862,
+                                                            "count": 64088,
                                                             "is_parallel": true,
-                                                            "self": 6.735939079007807,
+                                                            "self": 21.903551322022167,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 29.435590543989974,
-                                                                    "count": 182030,
+                                                                    "total": 85.52562374401646,
+                                                                    "count": 512704,
                                                                     "is_parallel": true,
-                                                                    "self": 29.435590543989974
+                                                                    "self": 85.52562374401646
                                                                 }
                                                             }
                                                         }
@@ -305,53 +341,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 0.00015533200007666892,
-                    "count": 1,
-                    "self": 0.00015533200007666892,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 665.684246787986,
+                            "count": 64089,
+                            "self": 3.2633626090516827,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 481.74200125804015,
-                                    "count": 475801,
-                                    "is_parallel": true,
-                                    "self": 10.128154182054175,
+                                "process_trajectory": {
+                                    "total": 114.8632097159284,
+                                    "count": 64089,
+                                    "self": 114.65232952292808,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 267.8717545559862,
-                                            "count": 475801,
-                                            "is_parallel": true,
-                                            "self": 266.3726373989862,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 1.4991171569999437,
-                                                    "count": 4,
-                                                    "is_parallel": true,
-                                                    "self": 1.4991171569999437
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 203.74209251999977,
-                                            "count": 90,
-                                            "is_parallel": true,
-                                            "self": 75.32750616000109,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 128.41458635999868,
-                                                    "count": 4584,
-                                                    "is_parallel": true,
-                                                    "self": 128.41458635999868
-                                                }
-                                            }
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.21088019300032101,
+                                            "count": 2,
+                                            "self": 0.21088019300032101
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 547.5576744630059,
+                                    "count": 453,
+                                    "self": 349.3483743630095,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 198.20930009999643,
+                                            "count": 22788,
+                                            "self": 198.20930009999643
                                         }
                                     }
                                 }
@@ -359,15 +375,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.2820000847568735e-06,
+                    "count": 1,
+                    "self": 1.2820000847568735e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.143623080999987,
+                    "total": 0.09334821500033286,
                     "count": 1,
-                    "self": 0.0009553270000424163,
+                    "self": 0.0014316560004772327,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.14266775399994458,
+                            "total": 0.09191655899985562,
                             "count": 1,
-                            "self": 0.14266775399994458
+                            "self": 0.09191655899985562
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,59 +1,41 @@
 {
-    "SnowballTarget": {
+    "Pyramids": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 12.636363636363637,
-                "creation_time": 1688700948.9319053,
+                "steps": 499995,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499995.onnx",
+                "reward": null,
+                "creation_time": 1688703177.2259724,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499995.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 21.0,
-                "creation_time": 1688701072.297952,
+                "steps": 999977,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999977.onnx",
+                "reward": 1.5592857003211975,
+                "creation_time": 1688704470.3783426,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999977.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1688701192.3998864,
+                "steps": 1000105,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000105.onnx",
+                "reward": 1.5592857003211975,
+                "creation_time": 1688704470.481942,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
-                ]
-            },
-            {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 24.0,
-                "creation_time": 1688701310.9299247,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
-                ]
-            },
-            {
-                "steps": 200200,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
-                "reward": 24.681818181818183,
-                "creation_time": 1688701311.1254091,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000105.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200200,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 24.681818181818183,
-            "creation_time": 1688701311.1254091,
+            "steps": 1000105,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.5592857003211975,
+            "creation_time": 1688704470.481942,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000105.pt"
             ]
         }
     },