First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b94b001242358b03da82f81489f13248bd13181f0f1dad14be8d64f2148407
+size 1420238

Pyramids/Pyramids-1000068.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b94b001242358b03da82f81489f13248bd13181f0f1dad14be8d64f2148407
+size 1420238

Pyramids/Pyramids-1000068.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c57819f276be7f1be9b98e0e6561c8129ce74c4840519f33ecf30f582b8af3
+size 8656252

Pyramids/Pyramids-499959.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a30a5d5d5b192bc5f717c35ad5fa12cd0b0b86fbfbd5a1fc1ac20000d9cb19
+size 1420238

Pyramids/Pyramids-499959.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf6072795f33adac74740e84807dcb8c3f8889fcaa51083c323bc4fa3190636
+size 8656173

Pyramids/Pyramids-999940.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b94b001242358b03da82f81489f13248bd13181f0f1dad14be8d64f2148407
+size 1420238

Pyramids/Pyramids-999940.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0945df394eafdb4170ab51339e4a9fdaac784a8f1aba7db2ece6649b1796e66b
+size 8656173

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f44b5974941a50fd294ffbcd3692091c3a1ab391aaa99b16cdec5a3ff70ded
+size 8655778

Pyramids/events.out.tfevents.1700155027.db8ace4712c0.7395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42b92119183d126041c44ed6361fe64712cabfbeac3cf6b51c90aa964119528
+size 323918

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, "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}, "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, "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}, "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
@@ -65,7 +78,7 @@ 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] 55264 [Flags] 2 [Guid] 1023429672 [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: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  0.125 seconds
+- Completed reload, in  0.102 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: 0.905481 ms
+UnloadTime: 0.797823 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]: 6325 frames, [32.0 KB-64.0 KB]: 9334 frames, [64.0 KB-128.0 KB]: 3109 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 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 4]
+    [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_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]: 18470 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 11816
     [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]: 18768 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.7 MB
+      Peak Block count 3
+      Peak Allocated memory 29.8 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]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 23.8 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]: 4936 frames, [64.0 KB-128.0 KB]: 526 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.7 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]: 18769 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]: 18470 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]: 18768 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]: 18769 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]: 18769 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]: 18769 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":1700157421373,"processId":7412,"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": 0.8441686630249023,
-            "min": 0.8441686630249023,
-            "max": 2.871239185333252,
-            "count": 20
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.428602933883667,
+            "min": 0.4240873456001282,
+            "max": 1.4388667345046997,
+            "count": 33
         },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8050.83642578125,
-            "min": 8050.83642578125,
-            "max": 29372.77734375,
-            "count": 20
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 12906.091796875,
+            "min": 12688.693359375,
+            "max": 43649.4609375,
+            "count": 33
         },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.mean": {
+            "value": 989970.0,
+            "min": 29952.0,
+            "max": 989970.0,
+            "count": 33
         },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.sum": {
+            "value": 989970.0,
+            "min": 29952.0,
+            "max": 989970.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.993959426879883,
-            "min": 0.2630867660045624,
-            "max": 12.993959426879883,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.5296725630760193,
+            "min": -0.11762659251689911,
+            "max": 0.5977739691734314,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2533.822021484375,
-            "min": 51.03883361816406,
-            "max": 2618.63037109375,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 144.07093811035156,
+            "min": -28.465635299682617,
+            "max": 170.36558532714844,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.007292655762284994,
+            "min": -0.007292655762284994,
+            "max": 0.3651055097579956,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -1.9836024045944214,
+            "min": -1.9836024045944214,
+            "max": 88.35552978515625,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06948945624069038,
-            "min": 0.06201119307515197,
-            "max": 0.07423860222579427,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06946116828099441,
+            "min": 0.06611923583093848,
+            "max": 0.07254277574496326,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2779578249627615,
-            "min": 0.24804477230060787,
-            "max": 0.37119301112897135,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0419175242149161,
+            "min": 0.4736866809885371,
+            "max": 1.0646841762109214,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.19756650701895648,
-            "min": 0.10566313002559849,
-            "max": 0.30153941304660314,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.017217376264302194,
+            "min": 0.000491823542535466,
+            "max": 0.01770960290256577,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7902660280758259,
-            "min": 0.42265252010239396,
-            "max": 1.3938179977384269,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.2582606439645329,
+            "min": 0.005410058967890126,
+            "max": 0.2582606439645329,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.587457470880002e-06,
+            "min": 7.587457470880002e-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": 0.00011381186206320002,
+            "min": 0.00011381186206320002,
+            "max": 0.0036331411889529994,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10252912000000002,
+            "min": 0.10252912000000002,
+            "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": 1.5379368000000002,
+            "min": 1.3886848,
+            "max": 2.6110469999999997,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0002626590880000001,
+            "min": 0.0002626590880000001,
+            "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": 0.003939886320000001,
+            "min": 0.003939886320000001,
+            "max": 0.12112359530000001,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.84090909090909,
-            "min": 3.090909090909091,
-            "max": 25.84090909090909,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.014557884074747562,
+            "min": 0.014557884074747562,
+            "max": 0.49442628026008606,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1137.0,
-            "min": 136.0,
-            "max": 1415.0,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.218368262052536,
+            "min": 0.20432652533054352,
+            "max": 3.460983991622925,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.84090909090909,
-            "min": 3.090909090909091,
-            "max": 25.84090909090909,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 363.2564102564103,
+            "min": 308.8556701030928,
+            "max": 999.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1137.0,
-            "min": 136.0,
-            "max": 1415.0,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28334.0,
+            "min": 15984.0,
+            "max": 32316.0,
+            "count": 33
         },
-        "SnowballTarget.IsTraining.mean": {
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.5854512565793135,
+            "min": -1.0000000521540642,
+            "max": 1.6499030748286199,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 123.66519801318645,
+            "min": -31.997201651334763,
+            "max": 160.04059825837612,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.5854512565793135,
+            "min": -1.0000000521540642,
+            "max": 1.6499030748286199,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 123.66519801318645,
+            "min": -31.997201651334763,
+            "max": 160.04059825837612,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.054531377216335386,
+            "min": 0.05044994874468515,
+            "max": 10.087773490697145,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 4.25344742287416,
+            "min": 4.25344742287416,
+            "max": 161.40437585115433,
+            "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": "1700154102",
+        "start_time_seconds": "1700155026",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "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": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.0+cu118",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1700154604"
+        "end_time_seconds": "1700157421"
     },
-    "total": 502.35995868400005,
+    "total": 2394.462917179,
     "count": 1,
-    "self": 0.7906019990000459,
+    "self": 0.47672261400020943,
     "children": {
         "run_training.setup": {
-            "total": 0.07296706500005712,
+            "total": 0.04562203199998294,
             "count": 1,
-            "self": 0.07296706500005712
+            "self": 0.04562203199998294
         },
         "TrainerController.start_learning": {
-            "total": 501.49638961999995,
+            "total": 2393.9405725330002,
             "count": 1,
-            "self": 0.6495832899950074,
+            "self": 1.6336691000274186,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 8.798982468999952,
+                    "total": 4.573602327999879,
                     "count": 1,
-                    "self": 8.798982468999952
+                    "self": 4.573602327999879
                 },
                 "TrainerController.advance": {
-                    "total": 491.92038092100495,
-                    "count": 18204,
-                    "self": 0.3146741170126006,
+                    "total": 2387.6498104919724,
+                    "count": 63931,
+                    "self": 1.7738278268316208,
                     "children": {
                         "env_step": {
-                            "total": 491.60570680399235,
-                            "count": 18204,
-                            "self": 339.0497773479975,
+                            "total": 1728.7174099060971,
+                            "count": 63931,
+                            "self": 1579.7855124230505,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 152.2353009289959,
-                                    "count": 18204,
-                                    "self": 1.5863792399995873,
+                                    "total": 147.91372851701226,
+                                    "count": 63931,
+                                    "self": 5.1241297769854555,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 150.64892168899632,
-                                            "count": 18204,
-                                            "self": 150.64892168899632
+                                            "total": 142.7895987400268,
+                                            "count": 62563,
+                                            "self": 142.7895987400268
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.32062852699891664,
-                                    "count": 18204,
+                                    "total": 1.018168966034409,
+                                    "count": 63931,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 499.83919157899163,
-                                            "count": 18204,
+                                            "total": 2388.6713924379565,
+                                            "count": 63931,
                                             "is_parallel": true,
-                                            "self": 240.95780052200826,
+                                            "self": 939.156370706047,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0076921050000464675,
+                                                            "total": 0.0019086770000740216,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.005449647999739682,
+                                                            "self": 0.0006004250001296896,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0022424570003067856,
-                                                                    "count": 10,
+                                                                    "total": 0.001308251999944332,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0022424570003067856
+                                                                    "self": 0.001308251999944332
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06552012300005572,
+                                                            "total": 0.08896567900001173,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006380760000865848,
+                                                            "self": 0.0005596610001248337,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003875419999985752,
+                                                                    "total": 0.0005038300000705931,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003875419999985752
+                                                                    "self": 0.0005038300000705931
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.062444893000019874,
+                                                                    "total": 0.08623267799998757,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.062444893000019874
+                                                                    "self": 0.08623267799998757
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0020496119999506845,
+                                                                    "total": 0.0016695099998287333,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003644929998927182,
+                                                                    "self": 0.0003595539997149899,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0016851190000579663,
-                                                                            "count": 10,
+                                                                            "total": 0.0013099560001137434,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0016851190000579663
+                                                                            "self": 0.0013099560001137434
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 258.8813910569834,
-                                                    "count": 18203,
+                                                    "total": 1449.5150217319094,
+                                                    "count": 63930,
                                                     "is_parallel": true,
-                                                    "self": 11.06817828800206,
+                                                    "self": 36.06239119688098,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.592213340002218,
-                                                            "count": 18203,
+                                                            "total": 24.25869536602886,
+                                                            "count": 63930,
                                                             "is_parallel": true,
-                                                            "self": 5.592213340002218
+                                                            "self": 24.25869536602886
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 206.92956483999126,
-                                                            "count": 18203,
+                                                            "total": 1287.5401344009586,
+                                                            "count": 63930,
                                                             "is_parallel": true,
-                                                            "self": 206.92956483999126
+                                                            "self": 1287.5401344009586
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 35.29143458898784,
-                                                            "count": 18203,
+                                                            "total": 101.65380076804104,
+                                                            "count": 63930,
                                                             "is_parallel": true,
-                                                            "self": 6.980554716060169,
+                                                            "self": 21.33768137311131,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 28.31087987292767,
-                                                                    "count": 182030,
+                                                                    "total": 80.31611939492973,
+                                                                    "count": 511440,
                                                                     "is_parallel": true,
-                                                                    "self": 28.31087987292767
+                                                                    "self": 80.31611939492973
                                                                 }
                                                             }
                                                         }
@@ -305,53 +341,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 0.00016235899988714664,
-                    "count": 1,
-                    "self": 0.00016235899988714664,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 657.1585727590436,
+                            "count": 63931,
+                            "self": 3.1148075160595,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 487.93016638804204,
-                                    "count": 514605,
-                                    "is_parallel": true,
-                                    "self": 10.725942998065989,
+                                "process_trajectory": {
+                                    "total": 126.86145943998463,
+                                    "count": 63931,
+                                    "self": 126.69525581998505,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 275.5798138519766,
-                                            "count": 514605,
-                                            "is_parallel": true,
-                                            "self": 274.24029960097687,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 1.3395142509997413,
-                                                    "count": 4,
-                                                    "is_parallel": true,
-                                                    "self": 1.3395142509997413
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 201.62440953799944,
-                                            "count": 90,
-                                            "is_parallel": true,
-                                            "self": 64.44281431099535,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 137.1815952270041,
-                                                    "count": 4584,
-                                                    "is_parallel": true,
-                                                    "self": 137.1815952270041
-                                                }
-                                            }
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.16620361999957822,
+                                            "count": 2,
+                                            "self": 0.16620361999957822
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 527.1823058029995,
+                                    "count": 454,
+                                    "self": 316.2655701059905,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 210.91673569700902,
+                                            "count": 22794,
+                                            "self": 210.91673569700902
                                         }
                                     }
                                 }
@@ -359,15 +375,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.2710006558336318e-06,
+                    "count": 1,
+                    "self": 1.2710006558336318e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.12728058100015005,
+                    "total": 0.08348934199966607,
                     "count": 1,
-                    "self": 0.001159382000196274,
+                    "self": 0.0015438289992744103,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12612119899995378,
+                            "total": 0.08194551300039166,
                             "count": 1,
-                            "self": 0.12612119899995378
+                            "self": 0.08194551300039166
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,59 +1,41 @@
 {
-    "SnowballTarget": {
+    "Pyramids": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 14.090909090909092,
-                "creation_time": 1700154238.246119,
+                "steps": 499959,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499959.onnx",
+                "reward": 0.8835333064198494,
+                "creation_time": 1700156147.9972775,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499959.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 22.545454545454547,
-                "creation_time": 1700154362.677398,
+                "steps": 999940,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999940.onnx",
+                "reward": 1.791599953174591,
+                "creation_time": 1700157420.8301928,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999940.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 25.818181818181817,
-                "creation_time": 1700154483.9611332,
+                "steps": 1000068,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000068.onnx",
+                "reward": 1.791599953174591,
+                "creation_time": 1700157420.9255075,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
-                ]
-            },
-            {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 24.90909090909091,
-                "creation_time": 1700154603.8712096,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 24.90909090909091,
-                "creation_time": 1700154604.0296245,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000068.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 24.90909090909091,
-            "creation_time": 1700154604.0296245,
+            "steps": 1000068,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.791599953174591,
+            "creation_time": 1700157420.9255075,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000068.pt"
             ]
         }
     },