First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a19d8bd7541c9c6801cdd0e6aa841e176c4af9b92ab2567a7100639d767bc8b
+size 1420238

Pyramids/Pyramids-1499982.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72108a4ec15f6a6d49585bbdedaa0e058726306f30ec0beeffd6b561c872918b
+size 1420238

Pyramids/Pyramids-1499982.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2462d9732511f311746e334aed25e0e40b7a82077bd4e8f6542ca7c7fb9e5bbe
+size 8656252

Pyramids/Pyramids-1999961.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52580e0536558acca026a4cd05ce0fe46dbc9a375591c20683b0af127b6fb5a4
+size 1420238

Pyramids/Pyramids-1999961.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9e566c22b965ac4290269fc77b66dc2f8b2b4440948c03c606daf790932a1e
+size 8656252

Pyramids/Pyramids-2499890.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3a17897932bf090e95c2c2db87019c7438f3f287540263566316d075a82bff
+size 1420238

Pyramids/Pyramids-2499890.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4437eb0ea5c90e8353901708344cd2fb09c4ab4eff86126066753bab6c32a81
+size 8656252

Pyramids/Pyramids-2999946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a19d8bd7541c9c6801cdd0e6aa841e176c4af9b92ab2567a7100639d767bc8b
+size 1420238

Pyramids/Pyramids-2999946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374c485a43f2dd9c07f975adadace83c2f3f7ff6434b6fc3f4c9376f7312558b
+size 8656252

Pyramids/Pyramids-3000074.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a19d8bd7541c9c6801cdd0e6aa841e176c4af9b92ab2567a7100639d767bc8b
+size 1420238

Pyramids/Pyramids-3000074.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ab5c70f8abe62eaca6f4b6d3abe9f371d048e25a09dc36019bf1c35cf83f00
+size 8656252

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffffaed607d41d573c63c4ef0c87113c72fad17b887f083618de92f36a59fe6
+size 8655778

Pyramids/events.out.tfevents.1707641309.86300a74e86c.9537.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfd92a60087fea560cb72961cb5b9cff9ccbd67309ed913aecf86b5b2d62125
+size 970929

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": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training1", "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: 3000000
+    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 Training1
   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] 55278 [Flags] 2 [Guid] 4225365929 [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  0.098 seconds
+- Completed reload, in  0.096 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: 0.763460 ms
+UnloadTime: 0.805297 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]: 5368 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]: 10687 frames, [32.0 KB-64.0 KB]: 31160 frames, [64.0 KB-128.0 KB]: 14421 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]: 55970 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 36
+  Peak main deferred allocation count 12522
     [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]: 5460 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56268 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.7 MB
+      Peak Block count 3
+      Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56269 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 23.0 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]: 5063 frames, [64.0 KB-128.0 KB]: 397 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56268 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 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]: 5460 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 56269 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]: 5460 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55970 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]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 56268 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]: 5460 frames
+      Peak usage frame count: [0-1.0 KB]: 56269 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]: 5460 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56269 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]: 56269 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":1707648508834,"processId":9556,"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": 0.7945277690887451,
-            "min": 0.7945277690887451,
-            "max": 2.8587188720703125,
-            "count": 20
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.15904517471790314,
+            "min": 0.14119312167167664,
+            "max": 1.4430776834487915,
+            "count": 100
         },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 7586.1513671875,
-            "min": 7586.1513671875,
-            "max": 29307.5859375,
-            "count": 20
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4786.62353515625,
+            "min": 4231.275390625,
+            "max": 43777.203125,
+            "count": 100
         },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.mean": {
+            "value": 2999946.0,
+            "min": 29952.0,
+            "max": 2999946.0,
+            "count": 100
         },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.sum": {
+            "value": 2999946.0,
+            "min": 29952.0,
+            "max": 2999946.0,
+            "count": 100
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.168272018432617,
-            "min": 0.34102368354797363,
-            "max": 13.168272018432617,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.7888457179069519,
+            "min": -0.09573692083358765,
+            "max": 0.8402525186538696,
+            "count": 100
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2567.81298828125,
-            "min": 66.1585922241211,
-            "max": 2673.463623046875,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 235.07601928710938,
+            "min": -23.07259750366211,
+            "max": 257.95751953125,
+            "count": 100
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.0013666519662365317,
+            "min": -0.021632174029946327,
+            "max": 0.37051114439964294,
+            "count": 100
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -0.40726229548454285,
+            "min": -5.925553321838379,
+            "max": 87.81114196777344,
+            "count": 100
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07241338226623495,
-            "min": 0.06235784397804488,
-            "max": 0.07311035049474324,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.07264763730234423,
+            "min": 0.06444992081313912,
+            "max": 0.07344182118655408,
+            "count": 100
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2896535290649398,
-            "min": 0.2494313759121795,
-            "max": 0.3655517524737162,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0170669222328192,
+            "min": 0.4966073289209838,
+            "max": 1.0861939627302848,
+            "count": 100
         },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.19191494752086843,
-            "min": 0.11354467662179148,
-            "max": 0.30274705103799404,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015464918590926875,
+            "min": 0.00029515402018361465,
+            "max": 0.01685466549889598,
+            "count": 100
         },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7676597900834737,
-            "min": 0.4541787064871659,
-            "max": 1.5137352551899703,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21650886027297625,
+            "min": 0.0038370022623869906,
+            "max": 0.25281998248343973,
+            "count": 100
         },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.579520902097621e-06,
+            "min": 1.579520902097621e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
         },
-        "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.2113292629366695e-05,
+            "min": 2.2113292629366695e-05,
+            "max": 0.0039692628769124,
+            "count": 100
         },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10052647380952383,
+            "min": 0.10052647380952383,
+            "max": 0.19946118095238097,
+            "count": 100
         },
-        "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4073706333333336,
+            "min": 1.3962282666666668,
+            "max": 2.767424733333334,
+            "count": 100
         },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+        "Pyramids.Policy.Beta.mean": {
+            "value": 6.259473357142864e-05,
+            "min": 6.259473357142864e-05,
+            "max": 0.009946171977142856,
+            "count": 100
         },
-        "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.000876326270000001,
+            "min": 0.000876326270000001,
+            "max": 0.13231645124,
+            "count": 100
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.522727272727273,
-            "min": 3.090909090909091,
-            "max": 25.945454545454545,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.007360729854553938,
+            "min": 0.007156352046877146,
+            "max": 0.4330911338329315,
+            "count": 100
         },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1123.0,
-            "min": 136.0,
-            "max": 1427.0,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.10305021703243256,
+            "min": 0.10018892586231232,
+            "max": 3.0316379070281982,
+            "count": 100
         },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.522727272727273,
-            "min": 3.090909090909091,
-            "max": 25.945454545454545,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 248.22764227642276,
+            "min": 211.21641791044777,
+            "max": 999.0,
+            "count": 100
         },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1123.0,
-            "min": 136.0,
-            "max": 1427.0,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30532.0,
+            "min": 15984.0,
+            "max": 34165.0,
+            "count": 100
         },
-        "SnowballTarget.IsTraining.mean": {
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7029755998675415,
+            "min": -1.0000000521540642,
+            "max": 1.7886716305319943,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 209.46599878370762,
+            "min": -31.994001641869545,
+            "max": 248.88599736243486,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7029755998675415,
+            "min": -1.0000000521540642,
+            "max": 1.7886716305319943,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 209.46599878370762,
+            "min": -31.994001641869545,
+            "max": 248.88599736243486,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.01874860980000434,
+            "min": 0.016304011354424882,
+            "max": 8.773146278224885,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.306079005400534,
+            "min": 2.1763417135662166,
+            "max": 140.37034045159817,
+            "count": 100
+        },
+        "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 100
         },
-        "SnowballTarget.IsTraining.sum": {
+        "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 100
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1707639669",
+        "start_time_seconds": "1707641308",
         "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 Training1 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1707640103"
+        "end_time_seconds": "1707648508"
     },
-    "total": 433.35343815399995,
+    "total": 7200.284822367,
     "count": 1,
-    "self": 0.426371432999872,
+    "self": 0.5284415239993905,
     "children": {
         "run_training.setup": {
-            "total": 0.04948742700003095,
+            "total": 0.04663787100025729,
             "count": 1,
-            "self": 0.04948742700003095
+            "self": 0.04663787100025729
         },
         "TrainerController.start_learning": {
-            "total": 432.87757929400004,
+            "total": 7199.709742972,
             "count": 1,
-            "self": 0.5383631769922204,
+            "self": 3.8992054161790293,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.771140962000004,
+                    "total": 2.402931795999848,
                     "count": 1,
-                    "self": 3.771140962000004
+                    "self": 2.402931795999848
                 },
                 "TrainerController.advance": {
-                    "total": 428.47413212100787,
-                    "count": 18199,
-                    "self": 0.25004255101862327,
+                    "total": 7193.320404859821,
+                    "count": 194307,
+                    "self": 4.170448085907083,
                     "children": {
                         "env_step": {
-                            "total": 428.22408956998925,
-                            "count": 18199,
-                            "self": 278.400575802979,
+                            "total": 5290.6202441470305,
+                            "count": 194307,
+                            "self": 4909.299461818357,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 149.55717883000568,
-                                    "count": 18199,
-                                    "self": 1.420347408006137,
+                                    "total": 378.82628616780494,
+                                    "count": 194307,
+                                    "self": 13.983717686802265,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 148.13683142199955,
-                                            "count": 18199,
-                                            "self": 148.13683142199955
+                                            "total": 364.8425684810027,
+                                            "count": 187561,
+                                            "self": 364.8425684810027
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.266334937004558,
-                                    "count": 18199,
+                                    "total": 2.4944961608684935,
+                                    "count": 194307,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 431.81501716700427,
-                                            "count": 18199,
+                                            "total": 7184.112410649101,
+                                            "count": 194307,
                                             "is_parallel": true,
-                                            "self": 215.30535988299278,
+                                            "self": 2629.682749757172,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00620952600002056,
+                                                            "total": 0.0020520140001281106,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0047324110000772635,
+                                                            "self": 0.0006502109999928507,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014771149999432964,
-                                                                    "count": 10,
+                                                                    "total": 0.00140180300013526,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014771149999432964
+                                                                    "self": 0.00140180300013526
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.036022082000044975,
+                                                            "total": 0.048373163000178465,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008672569999816915,
+                                                            "self": 0.0005794289995719737,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00041549000002305547,
+                                                                    "total": 0.00045700100008616573,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00041549000002305547
+                                                                    "self": 0.00045700100008616573
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.032746697999982644,
+                                                                    "total": 0.045748019000257045,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.032746697999982644
+                                                                    "self": 0.045748019000257045
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019926370000575844,
+                                                                    "total": 0.0015887140002632805,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00039673000014772697,
+                                                                    "self": 0.0003393910001250333,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015959069999098574,
-                                                                            "count": 10,
+                                                                            "total": 0.0012493230001382472,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015959069999098574
+                                                                            "self": 0.0012493230001382472
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 216.5096572840115,
-                                                    "count": 18198,
+                                                    "total": 4554.4296608919285,
+                                                    "count": 194306,
                                                     "is_parallel": true,
-                                                    "self": 10.42615886100566,
+                                                    "self": 106.7503921042935,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.3869512640030734,
-                                                            "count": 18198,
+                                                            "total": 72.42947624292219,
+                                                            "count": 194306,
                                                             "is_parallel": true,
-                                                            "self": 5.3869512640030734
+                                                            "self": 72.42947624292219
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 167.64475050799876,
-                                                            "count": 18198,
+                                                            "total": 4077.8874620698484,
+                                                            "count": 194306,
                                                             "is_parallel": true,
-                                                            "self": 167.64475050799876
+                                                            "self": 4077.8874620698484
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 33.051796651004,
-                                                            "count": 18198,
+                                                            "total": 297.3623304748644,
+                                                            "count": 194306,
                                                             "is_parallel": true,
-                                                            "self": 6.04247532900024,
+                                                            "self": 58.62167341188933,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 27.009321322003757,
-                                                                    "count": 181980,
+                                                                    "total": 238.74065706297506,
+                                                                    "count": 1554448,
                                                                     "is_parallel": true,
-                                                                    "self": 27.009321322003757
+                                                                    "self": 238.74065706297506
                                                                 }
                                                             }
                                                         }
@@ -305,53 +341,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 0.00017670199997610325,
-                    "count": 1,
-                    "self": 0.00017670199997610325,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 1898.5297126268833,
+                            "count": 194307,
+                            "self": 8.17209160847733,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 423.0315505759635,
-                                    "count": 654588,
-                                    "is_parallel": true,
-                                    "self": 13.86601326296227,
+                                "process_trajectory": {
+                                    "total": 386.30167562139377,
+                                    "count": 194307,
+                                    "self": 385.7367878713944,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 232.55934040200145,
-                                            "count": 654588,
-                                            "is_parallel": true,
-                                            "self": 232.05074106200152,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 0.5085993399999325,
-                                                    "count": 4,
-                                                    "is_parallel": true,
-                                                    "self": 0.5085993399999325
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 176.60619691099976,
-                                            "count": 90,
-                                            "is_parallel": true,
-                                            "self": 54.72874049300435,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 121.8774564179954,
-                                                    "count": 4587,
-                                                    "is_parallel": true,
-                                                    "self": 121.8774564179954
-                                                }
-                                            }
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5648877499993432,
+                                            "count": 6,
+                                            "self": 0.5648877499993432
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1504.0559453970122,
+                                    "count": 1397,
+                                    "self": 890.0737098281561,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 613.9822355688561,
+                                            "count": 68412,
+                                            "self": 613.9822355688561
                                         }
                                     }
                                 }
@@ -359,15 +375,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.0180010576732457e-06,
+                    "count": 1,
+                    "self": 1.0180010576732457e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.09376633199997286,
+                    "total": 0.0871998819984583,
                     "count": 1,
-                    "self": 0.0010438780000185943,
+                    "self": 0.0015097789982974064,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09272245399995427,
+                            "total": 0.08569010300016089,
                             "count": 1,
-                            "self": 0.09272245399995427
+                            "self": 0.08569010300016089
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,59 +1,59 @@
 {
-    "SnowballTarget": {
+    "Pyramids": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 14.0,
-                "creation_time": 1707639781.9135616,
+                "steps": 1499982,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-1499982.onnx",
+                "reward": 1.5844999998807907,
+                "creation_time": 1707644647.3277807,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-1499982.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1707639889.3723226,
+                "steps": 1999961,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-1999961.onnx",
+                "reward": null,
+                "creation_time": 1707645936.9663665,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-1999961.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.818181818181817,
-                "creation_time": 1707639996.157182,
+                "steps": 2499890,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-2499890.onnx",
+                "reward": 1.7240000069141388,
+                "creation_time": 1707647209.0462859,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-2499890.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.363636363636363,
-                "creation_time": 1707640102.4578862,
+                "steps": 2999946,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-2999946.onnx",
+                "reward": 1.742999980226159,
+                "creation_time": 1707648508.2705848,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-2999946.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.363636363636363,
-                "creation_time": 1707640102.5801744,
+                "steps": 3000074,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-3000074.onnx",
+                "reward": 1.742999980226159,
+                "creation_time": 1707648508.3680053,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-3000074.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.363636363636363,
-            "creation_time": 1707640102.5801744,
+            "steps": 3000074,
+            "file_path": "results/Pyramids Training1/Pyramids.onnx",
+            "reward": 1.742999980226159,
+            "creation_time": 1707648508.3680053,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/Pyramids Training1/Pyramids/Pyramids-3000074.pt"
             ]
         }
     },