First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a27d8b162e17908c0ded1b164d7a958d7a38aeaea5f5262e4cbee629f23bb4b
+size 1420238

Pyramids/Pyramids-1000099.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a27d8b162e17908c0ded1b164d7a958d7a38aeaea5f5262e4cbee629f23bb4b
+size 1420238

Pyramids/Pyramids-1000099.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c174f9c37938ea0bd115835ed3745510185ad8cc6e8fc4f426eec5274b3a267
+size 8656252

Pyramids/Pyramids-499977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df4d140d545262366e0c1538989a2b7d283140b7b71bd65d21422a28531044d
+size 1420238

Pyramids/Pyramids-499977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a58dd876231d6f46f44ac73305bee20d6e33b7c3d56c514c3950631ca71619
+size 8656173

Pyramids/Pyramids-999971.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a27d8b162e17908c0ded1b164d7a958d7a38aeaea5f5262e4cbee629f23bb4b
+size 1420238

Pyramids/Pyramids-999971.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d8d6c5921d725214746475c5f0328ec50f30332835b0b223ecfa6dab188644
+size 8656173

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2469dbed118313a2373479598e28e48ce9d5072668030fe6ab6e001ec92e6ade
+size 8655778

Pyramids/events.out.tfevents.1716961549.04af16f9a322.2208.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8310151692afa795f53fae2fac67f4881a730e168de0b8132ce657626d5b87dd
+size 314025

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, "no_graphics_monitor": false}, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

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
@@ -66,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 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] 55184 [Flags] 2 [Guid] 1537555317 [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  0.111 seconds
+- Completed reload, in  0.143 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: 0.937761 ms
+UnloadTime: 1.084545 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]: 3214 frames, [32.0 KB-64.0 KB]: 13546 frames, [64.0 KB-128.0 KB]: 2005 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]: 18467 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 44
+  Peak main deferred allocation count 12185
     [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]: 18764 frames, [32.0 MB-64.0 MB]: 1 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.6 MB
+      Peak Block count 3
+      Peak Allocated memory 32.1 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]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 22.0 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]: 4842 frames, [64.0 KB-128.0 KB]: 620 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18765 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.4 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]: 18766 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]: 18467 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]: 18765 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]: 18766 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]: 18766 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]: 18766 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":1716963817799,"processId":2259,"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": 1.0261160135269165,
-            "min": 1.0261160135269165,
-            "max": 2.8668124675750732,
-            "count": 20
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.5882905125617981,
+            "min": 0.5882905125617981,
+            "max": 1.4445035457611084,
+            "count": 33
         },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9831.2177734375,
-            "min": 9831.2177734375,
-            "max": 29390.5625,
-            "count": 20
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 17705.19140625,
+            "min": 17705.19140625,
+            "max": 43820.4609375,
+            "count": 33
         },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.mean": {
+            "value": 989958.0,
+            "min": 29952.0,
+            "max": 989958.0,
+            "count": 33
         },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.sum": {
+            "value": 989958.0,
+            "min": 29952.0,
+            "max": 989958.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.462175369262695,
-            "min": 0.4327087700366974,
-            "max": 12.462175369262695,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.19378341734409332,
+            "min": -0.09713666886091232,
+            "max": 0.32777920365333557,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2430.124267578125,
-            "min": 83.94550323486328,
-            "max": 2507.5517578125,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 49.22098922729492,
+            "min": -23.312801361083984,
+            "max": 84.56703186035156,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.30712687969207764,
+            "min": -0.4465263783931732,
+            "max": 0.778298556804657,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -78.0102310180664,
+            "min": -115.65032958984375,
+            "max": 184.45675659179688,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06412563032923643,
-            "min": 0.06207475551013439,
-            "max": 0.07407555559115922,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06753586639194613,
+            "min": 0.06624800781125241,
+            "max": 0.07580704509421314,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.25650252131694573,
-            "min": 0.24829902204053755,
-            "max": 0.37037777795579613,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9455021294872458,
+            "min": 0.512265932213665,
+            "max": 1.061762715592825,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.19697367787068965,
-            "min": 0.13397410634092474,
-            "max": 0.28771474102840705,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.01853889180707045,
+            "min": 8.666716704617517e-05,
+            "max": 0.035699201114766765,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7878947114827586,
-            "min": 0.535896425363699,
-            "max": 1.3323783000894622,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.2595444852989863,
+            "min": 0.0012133403386464523,
+            "max": 0.4997888156067347,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291906002698,
-            "count": 20
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.44860466002143e-06,
+            "min": 7.44860466002143e-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": 0.00010428046524030002,
+            "min": 0.00010428046524030002,
+            "max": 0.0033828749723751007,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19730199999999998,
-            "count": 20
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10248283571428574,
+            "min": 0.10248283571428574,
+            "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": 1.4347597000000003,
+            "min": 1.3691136000000002,
+            "max": 2.5276249000000006,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.004865369800000001,
-            "count": 20
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0002580352878571429,
+            "min": 0.0002580352878571429,
+            "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": 0.0036124940300000007,
+            "min": 0.0036124940300000007,
+            "max": 0.11278972751,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.704545454545453,
-            "min": 3.5681818181818183,
-            "max": 24.818181818181817,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.011106963269412518,
+            "min": 0.011106963269412518,
+            "max": 0.6607980728149414,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1087.0,
-            "min": 157.0,
-            "max": 1365.0,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.1554974913597107,
+            "min": 0.1554974913597107,
+            "max": 4.62558650970459,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.704545454545453,
-            "min": 3.5681818181818183,
-            "max": 24.818181818181817,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 608.5217391304348,
+            "min": 531.1509433962265,
+            "max": 999.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1087.0,
-            "min": 157.0,
-            "max": 1365.0,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 27992.0,
+            "min": 15984.0,
+            "max": 32649.0,
+            "count": 33
         },
-        "SnowballTarget.IsTraining.mean": {
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 0.8695782290204711,
+            "min": -1.0000000521540642,
+            "max": 1.2100481197789863,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 40.00059853494167,
+            "min": -32.000001668930054,
+            "max": 65.34259846806526,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 0.8695782290204711,
+            "min": -1.0000000521540642,
+            "max": 1.2100481197789863,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 40.00059853494167,
+            "min": -32.000001668930054,
+            "max": 65.34259846806526,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.07021384063061661,
+            "min": 0.06812311311174805,
+            "max": 14.008263183757663,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.229836669008364,
+            "min": 3.229836669008364,
+            "max": 224.1322109401226,
+            "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": "1716956272",
+        "start_time_seconds": "1716961548",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1716956871"
+        "end_time_seconds": "1716963817"
     },
-    "total": 598.4817274549999,
+    "total": 2269.1189995590003,
     "count": 1,
-    "self": 0.5898531829999456,
+    "self": 0.49157672700039257,
     "children": {
         "run_training.setup": {
-            "total": 0.11166007699998204,
+            "total": 0.05864394899998615,
             "count": 1,
-            "self": 0.11166007699998204
+            "self": 0.05864394899998615
         },
         "TrainerController.start_learning": {
-            "total": 597.780214195,
+            "total": 2268.568778883,
             "count": 1,
-            "self": 0.8202556349971246,
+            "self": 1.8625474419845887,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.37051059800001,
+                    "total": 3.2071996079999963,
                     "count": 1,
-                    "self": 3.37051059800001
+                    "self": 3.2071996079999963
                 },
                 "TrainerController.advance": {
-                    "total": 593.4815753940028,
-                    "count": 18205,
-                    "self": 0.45092544600368,
+                    "total": 2263.4090639290157,
+                    "count": 63293,
+                    "self": 1.9481654989808703,
                     "children": {
                         "env_step": {
-                            "total": 593.0306499479991,
-                            "count": 18205,
-                            "self": 456.1636353550118,
+                            "total": 1594.0946936410244,
+                            "count": 63293,
+                            "self": 1428.9048318720334,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 136.45623422299403,
-                                    "count": 18205,
-                                    "self": 2.3292680459913697,
+                                    "total": 164.03504797097816,
+                                    "count": 63293,
+                                    "self": 5.8489514269800225,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 134.12696617700266,
-                                            "count": 18205,
-                                            "self": 134.12696617700266
+                                            "total": 158.18609654399813,
+                                            "count": 62552,
+                                            "self": 158.18609654399813
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.41078036999329015,
-                                    "count": 18205,
+                                    "total": 1.1548137980128104,
+                                    "count": 63293,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 595.7561791449991,
-                                            "count": 18205,
+                                            "total": 2262.2840666509446,
+                                            "count": 63293,
                                             "is_parallel": true,
-                                            "self": 280.8093399830107,
+                                            "self": 982.955389554973,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005776978000000099,
+                                                            "total": 0.005019709999999122,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003974964000036607,
+                                                            "self": 0.0034935729999574505,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001802013999963492,
-                                                                    "count": 10,
+                                                                    "total": 0.0015261370000416719,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001802013999963492
+                                                                    "self": 0.0015261370000416719
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05118541299998469,
+                                                            "total": 0.048932879999995293,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000861774999947329,
+                                                            "self": 0.0006687089999672935,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044421200001920624,
+                                                                    "total": 0.0005017729999963194,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044421200001920624
+                                                                    "self": 0.0005017729999963194
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04745159400002308,
+                                                                    "total": 0.04589852399999472,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04745159400002308
+                                                                    "self": 0.04589852399999472
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002427831999995078,
+                                                                    "total": 0.001863874000036958,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00043859100000531726,
+                                                                    "self": 0.00038676999992048877,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001989240999989761,
-                                                                            "count": 10,
+                                                                            "total": 0.0014771040001164693,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001989240999989761
+                                                                            "self": 0.0014771040001164693
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 314.9468391619884,
-                                                    "count": 18204,
+                                                    "total": 1279.3286770959717,
+                                                    "count": 63292,
                                                     "is_parallel": true,
-                                                    "self": 14.911874367967187,
+                                                    "self": 38.96720433284827,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 7.540534548002711,
-                                                            "count": 18204,
+                                                            "total": 26.104903243049932,
+                                                            "count": 63292,
                                                             "is_parallel": true,
-                                                            "self": 7.540534548002711
+                                                            "self": 26.104903243049932
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 248.1692483610083,
-                                                            "count": 18204,
+                                                            "total": 1102.0334595860165,
+                                                            "count": 63292,
                                                             "is_parallel": true,
-                                                            "self": 248.1692483610083
+                                                            "self": 1102.0334595860165
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 44.32518188501021,
-                                                            "count": 18204,
+                                                            "total": 112.22310993405688,
+                                                            "count": 63292,
                                                             "is_parallel": true,
-                                                            "self": 8.744466119997526,
+                                                            "self": 24.23261198010522,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 35.580715765012684,
-                                                                    "count": 182040,
+                                                                    "total": 87.99049795395166,
+                                                                    "count": 506336,
                                                                     "is_parallel": true,
-                                                                    "self": 35.580715765012684
+                                                                    "self": 87.99049795395166
                                                                 }
                                                             }
                                                         }
@@ -305,53 +341,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 0.0001787500000318687,
-                    "count": 1,
-                    "self": 0.0001787500000318687,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 667.3662047890106,
+                            "count": 63293,
+                            "self": 3.3630484290450795,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 586.7525203629544,
-                                    "count": 782449,
-                                    "is_parallel": true,
-                                    "self": 17.61014896598158,
+                                "process_trajectory": {
+                                    "total": 138.291096423966,
+                                    "count": 63293,
+                                    "self": 137.9474408289658,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 315.3310648319727,
-                                            "count": 782449,
-                                            "is_parallel": true,
-                                            "self": 314.49197005397264,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 0.8390947780000602,
-                                                    "count": 4,
-                                                    "is_parallel": true,
-                                                    "self": 0.8390947780000602
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 253.81130656500014,
-                                            "count": 90,
-                                            "is_parallel": true,
-                                            "self": 72.38727000399555,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 181.42403656100458,
-                                                    "count": 4581,
-                                                    "is_parallel": true,
-                                                    "self": 181.42403656100458
-                                                }
-                                            }
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.34365559500020026,
+                                            "count": 2,
+                                            "self": 0.34365559500020026
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 525.7120599359995,
+                                    "count": 441,
+                                    "self": 311.2895666680187,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 214.42249326798077,
+                                            "count": 22830,
+                                            "self": 214.42249326798077
                                         }
                                     }
                                 }
@@ -359,15 +375,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.0200001270277426e-06,
+                    "count": 1,
+                    "self": 1.0200001270277426e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.10769381800002975,
+                    "total": 0.08996688399975028,
                     "count": 1,
-                    "self": 0.0015266079999491922,
+                    "self": 0.0015897059997769247,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10616721000008056,
+                            "total": 0.08837717799997336,
                             "count": 1,
-                            "self": 0.10616721000008056
+                            "self": 0.08837717799997336
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,59 +1,41 @@
 {
-    "SnowballTarget": {
+    "Pyramids": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.181818181818182,
-                "creation_time": 1716956423.2527618,
+                "steps": 499977,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499977.onnx",
+                "reward": null,
+                "creation_time": 1716962649.0265586,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499977.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 20.90909090909091,
-                "creation_time": 1716956568.9684863,
+                "steps": 999971,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999971.onnx",
+                "reward": null,
+                "creation_time": 1716963817.2782423,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999971.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.272727272727273,
-                "creation_time": 1716956721.802465,
+                "steps": 1000099,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000099.onnx",
+                "reward": null,
+                "creation_time": 1716963817.3791833,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
-                ]
-            },
-            {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 23.90909090909091,
-                "creation_time": 1716956870.412499,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 23.90909090909091,
-                "creation_time": 1716956870.5524566,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000099.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 23.90909090909091,
-            "creation_time": 1716956870.5524566,
+            "steps": 1000099,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1716963817.3791833,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000099.pt"
             ]
         }
     },