First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b957e51ff8945a4d6c983b241bae3a5b78121b118b26cea3f9bfc3f0316c0971
+size 1418184

Pyramids/Pyramids-1000033.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b957e51ff8945a4d6c983b241bae3a5b78121b118b26cea3f9bfc3f0316c0971
+size 1418184

Pyramids/Pyramids-1000033.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb1b43c348d65c099aeb0bbb48fdceb627ad3d4b055a07f3e5594103de90fb3
+size 8650990

Pyramids/Pyramids-499990.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c473a4caa4fde5c20572b3f2ec2a147766dc98c43f198f24f5478dd84c61673
+size 1418184

Pyramids/Pyramids-499990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998b7d2588566e34d366af986332eb7625cce61884cd1e6448f0f793728b32bf
+size 8650990

Pyramids/Pyramids-999996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b957e51ff8945a4d6c983b241bae3a5b78121b118b26cea3f9bfc3f0316c0971
+size 1418184

Pyramids/Pyramids-999996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e037edc1d2eb62dae862112c17a3e380dc5d0647cb6b9a939b208b4f5d9418
+size 8650990

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb1b43c348d65c099aeb0bbb48fdceb627ad3d4b055a07f3e5594103de90fb3
+size 8650990

Pyramids/events.out.tfevents.1679531446.f6843f43a72c.1643.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a64850097a1218d5b9011e3643e3af92232e94705cac43e6e5cdc2c2bd658017
+size 305063

README.md

@@ -1,10 +1,10 @@
 ---
 library_name: ml-agents
 tags:
-- SnowballTarget
+- Pyramids
 - deep-reinforcement-learning
 - reinforcement-learning
-- ML-Agents-SnowballTarget
+- ML-Agents-Pyramids
 ---
 
   # **ppo** Agent playing **SnowballTarget**

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -1,12 +1,12 @@
 default_settings: null
 behaviors:
-  SnowballTarget:
+  Pyramids:
     trainer_type: ppo
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.01
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -14,10 +14,10 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 50000
+    checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 256
+      hidden_units: 512
       num_layers: 2
       vis_encode_type: simple
       memory: null
@@ -35,17 +35,30 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
     init_path: null
-    keep_checkpoints: 10
+    keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 200000
-    time_horizon: 64
-    summary_freq: 10000
-    threaded: true
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -64,7 +77,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: Pyramids Training
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,14 @@
-Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 172.28.0.12
+Multi-casting "[IP] 172.28.0.12 [Port] 55141 [Flags] 2 [Guid] 1543193953 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
 Unable to load player prefs
-Initialize engine version: 2021.3.14f1 (eee1884e7226)
-[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -34,10 +36,31 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.082 seconds
+- Completed reload, in  0.140 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: 0.706741 ms
+UnloadTime: 1.133247 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]: 7055 frames, [32.0 KB-64.0 KB]: 8507 frames, [64.0 KB-128.0 KB]: 3206 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -143,48 +171,64 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 3]
+    [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 4]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_BatchDeleteObjects]
+    [ALLOC_TEMP_EnlightenWorker]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.6 MB
+  Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 40
+  Peak main deferred allocation count 12584
     [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]: 18768 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.6 MB
+      Peak Block count 3
+      Peak Allocated memory 31.5 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]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 22.3 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]: 4100 frames, [64.0 KB-128.0 KB]: 1360 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 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]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 39.6 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
 [ALLOC_CACHEOBJECTS] Dual Thread Allocator
-  Peak main deferred allocation count 0
+  Peak main deferred allocation count 1
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.6 MB
+      Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 2.2 MB
+      Peak Block count 2
+      Peak Allocated memory 4.2 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 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]: 18769 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 5460 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18769 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.7 KB
+      Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18769 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 29.2 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679533824188,"processId":1667,"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": 0.8644562363624573,
-            "min": 0.8623812198638916,
-            "max": 2.8654985427856445,
-            "count": 20
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.48850154876708984,
+            "min": 0.48850154876708984,
+            "max": 1.4755275249481201,
+            "count": 33
         },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8244.3193359375,
-            "min": 8244.3193359375,
-            "max": 29534.693359375,
-            "count": 20
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 14733.20703125,
+            "min": 14733.20703125,
+            "max": 44761.6015625,
+            "count": 33
         },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.mean": {
+            "value": 989972.0,
+            "min": 29952.0,
+            "max": 989972.0,
+            "count": 33
         },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.sum": {
+            "value": 989972.0,
+            "min": 29952.0,
+            "max": 989972.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 11.939881324768066,
-            "min": 0.3642022907733917,
-            "max": 11.939881324768066,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.7176522016525269,
+            "min": -0.11127028614282608,
+            "max": 0.7176522016525269,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2328.27685546875,
-            "min": 70.65524291992188,
-            "max": 2415.591796875,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 209.554443359375,
+            "min": -26.816139221191406,
+            "max": 209.554443359375,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.0437835156917572,
+            "min": 0.008350442163646221,
+            "max": 0.3982731103897095,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 12.784786224365234,
+            "min": 2.313072443008423,
+            "max": 94.3907241821289,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06827011936633533,
-            "min": 0.06107891125230155,
-            "max": 0.0744981785651237,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.07546330550740961,
+            "min": 0.06476313198408751,
+            "max": 0.07546330550740961,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2730804774653413,
-            "min": 0.2536183153130753,
-            "max": 0.3724908928256185,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0564862771037344,
+            "min": 0.49460572164288946,
+            "max": 1.089465714719457,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1714306450357624,
-            "min": 0.08303125500770323,
-            "max": 0.27229725835370083,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015976831384163927,
+            "min": 0.00038802330399016234,
+            "max": 0.01612685448748784,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.6857225801430497,
-            "min": 0.3321250200308129,
-            "max": 1.3614862917685042,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.22367563937829496,
+            "min": 0.0038802330399016235,
+            "max": 0.2419028173123176,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.579961759092855e-06,
+            "min": 7.579961759092855e-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": 0.00010611946462729998,
+            "min": 0.00010611946462729998,
+            "max": 0.003136647254451,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10252662142857143,
+            "min": 0.10252662142857143,
+            "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": 1.4353727,
+            "min": 1.3886848,
+            "max": 2.400546,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00026240948071428567,
+            "min": 0.00026240948071428567,
+            "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": 0.0036737327299999996,
+            "min": 0.0036737327299999996,
+            "max": 0.10458034509999999,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 23.636363636363637,
-            "min": 2.6818181818181817,
-            "max": 23.636363636363637,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.011238059028983116,
+            "min": 0.011238059028983116,
+            "max": 0.46219751238822937,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1040.0,
-            "min": 118.0,
-            "max": 1296.0,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.15733282268047333,
+            "min": 0.15733282268047333,
+            "max": 3.235382556915283,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 23.636363636363637,
-            "min": 2.6818181818181817,
-            "max": 23.636363636363637,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 260.25210084033614,
+            "min": 252.47368421052633,
+            "max": 999.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1040.0,
-            "min": 118.0,
-            "max": 1296.0,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30970.0,
+            "min": 15984.0,
+            "max": 32496.0,
+            "count": 33
         },
-        "SnowballTarget.IsTraining.mean": {
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7395762583966983,
+            "min": -1.0000000521540642,
+            "max": 1.7395762583966983,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 205.2699984908104,
+            "min": -31.99920167028904,
+            "max": 205.2699984908104,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7395762583966983,
+            "min": -1.0000000521540642,
+            "max": 1.7395762583966983,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 205.2699984908104,
+            "min": -31.99920167028904,
+            "max": 205.2699984908104,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.030279496394618716,
+            "min": 0.030279496394618716,
+            "max": 9.224788644351065,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.5729805745650083,
+            "min": 3.5204053386405576,
+            "max": 147.59661830961704,
+            "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": "1679528667",
+        "start_time_seconds": "1679531440",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1679529126"
+        "end_time_seconds": "1679533824"
     },
-    "total": 458.613853794,
+    "total": 2384.234228023,
     "count": 1,
-    "self": 0.43349772700003086,
+    "self": 0.8961950160000924,
     "children": {
         "run_training.setup": {
-            "total": 0.10633177699997987,
+            "total": 0.169306038000002,
             "count": 1,
-            "self": 0.10633177699997987
+            "self": 0.169306038000002
         },
         "TrainerController.start_learning": {
-            "total": 458.07402429,
+            "total": 2383.168726969,
             "count": 1,
-            "self": 0.5641953170057263,
+            "self": 1.6546354450665604,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 9.685632887999986,
+                    "total": 9.852543793000052,
                     "count": 1,
-                    "self": 9.685632887999986
+                    "self": 9.852543793000052
                 },
                 "TrainerController.advance": {
-                    "total": 447.6920177689944,
-                    "count": 18200,
-                    "self": 0.2749316810041478,
+                    "total": 2371.520595146933,
+                    "count": 63943,
+                    "self": 1.7681283489014277,
                     "children": {
                         "env_step": {
-                            "total": 447.41708608799024,
-                            "count": 18200,
-                            "self": 325.36833620101083,
+                            "total": 1709.8911882030268,
+                            "count": 63943,
+                            "self": 1586.2680713330087,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 121.78045260999124,
-                                    "count": 18200,
-                                    "self": 2.241966167994235,
+                                    "total": 122.64285272801783,
+                                    "count": 63943,
+                                    "self": 5.612532301032104,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 119.53848644199701,
-                                            "count": 18200,
-                                            "self": 119.53848644199701
+                                            "total": 117.03032042698572,
+                                            "count": 62561,
+                                            "self": 117.03032042698572
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.2682972769881644,
-                                    "count": 18200,
+                                    "total": 0.9802641420003511,
+                                    "count": 63943,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 456.61832608100366,
-                                            "count": 18200,
+                                            "total": 2377.2013677679856,
+                                            "count": 63943,
                                             "is_parallel": true,
-                                            "self": 216.02748321500326,
+                                            "self": 923.4828946680141,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005352686999970047,
+                                                            "total": 0.007448882000005597,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0040159309999694415,
+                                                            "self": 0.005019197999956759,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013367560000006051,
-                                                                    "count": 10,
+                                                                    "total": 0.0024296840000488373,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013367560000006051
+                                                                    "self": 0.0024296840000488373
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.051590693000036936,
+                                                            "total": 0.05169796599994925,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005862600000341445,
+                                                            "self": 0.0005603649998988658,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00045662600001605824,
+                                                                    "total": 0.0005421710000064195,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00045662600001605824
+                                                                    "self": 0.0005421710000064195
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04870257900000752,
+                                                                    "total": 0.04893172700002424,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04870257900000752
+                                                                    "self": 0.04893172700002424
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018452279999792154,
+                                                                    "total": 0.0016637030000197228,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040258499990386554,
+                                                                    "self": 0.0003772320000052787,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014426430000753498,
-                                                                            "count": 10,
+                                                                            "total": 0.0012864710000144441,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014426430000753498
+                                                                            "self": 0.0012864710000144441
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 240.5908428660004,
-                                                    "count": 18199,
+                                                    "total": 1453.7184730999716,
+                                                    "count": 63942,
                                                     "is_parallel": true,
-                                                    "self": 9.461800798994659,
+                                                    "self": 33.96729401390394,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.090131018001387,
-                                                            "count": 18199,
+                                                            "total": 25.660052194022455,
+                                                            "count": 63942,
                                                             "is_parallel": true,
-                                                            "self": 5.090131018001387
+                                                            "self": 25.660052194022455
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 195.4602854720046,
-                                                            "count": 18199,
+                                                            "total": 1289.1195084210135,
+                                                            "count": 63942,
                                                             "is_parallel": true,
-                                                            "self": 195.4602854720046
+                                                            "self": 1289.1195084210135
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 30.57862557699974,
-                                                            "count": 18199,
+                                                            "total": 104.97161847103172,
+                                                            "count": 63942,
                                                             "is_parallel": true,
-                                                            "self": 6.0104686960038975,
+                                                            "self": 23.163390141994796,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 24.568156880995843,
-                                                                    "count": 181990,
+                                                                    "total": 81.80822832903692,
+                                                                    "count": 511536,
                                                                     "is_parallel": true,
-                                                                    "self": 24.568156880995843
+                                                                    "self": 81.80822832903692
                                                                 }
                                                             }
                                                         }
@@ -305,53 +341,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 0.00011156699997627584,
-                    "count": 1,
-                    "self": 0.00011156699997627584,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 659.8612785950045,
+                            "count": 63943,
+                            "self": 2.829841813949315,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 444.6722346220029,
-                                    "count": 388058,
-                                    "is_parallel": true,
-                                    "self": 8.94076226099969,
+                                "process_trajectory": {
+                                    "total": 127.94745113905424,
+                                    "count": 63943,
+                                    "self": 127.4499458800542,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 246.1711357720052,
-                                            "count": 388058,
-                                            "is_parallel": true,
-                                            "self": 244.9877987850051,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 1.1833369870000752,
-                                                    "count": 4,
-                                                    "is_parallel": true,
-                                                    "self": 1.1833369870000752
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 189.56033658899804,
-                                            "count": 90,
-                                            "is_parallel": true,
-                                            "self": 71.40052082399467,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 118.15981576500337,
-                                                    "count": 4584,
-                                                    "is_parallel": true,
-                                                    "self": 118.15981576500337
-                                                }
-                                            }
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.49750525900003595,
+                                            "count": 2,
+                                            "self": 0.49750525900003595
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 529.0839856420009,
+                                    "count": 441,
+                                    "self": 336.7843891340056,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 192.29959650799532,
+                                            "count": 22833,
+                                            "self": 192.29959650799532
                                         }
                                     }
                                 }
@@ -359,15 +375,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.5790001270943321e-06,
+                    "count": 1,
+                    "self": 1.5790001270943321e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.13206674899993232,
+                    "total": 0.14095100500026092,
                     "count": 1,
-                    "self": 0.0008711059998631754,
+                    "self": 0.0020867940002062824,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.13119564300006914,
+                            "total": 0.13886421100005464,
                             "count": 1,
-                            "self": 0.13119564300006914
+                            "self": 0.13886421100005464
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,59 +1,41 @@
 {
-    "SnowballTarget": {
+    "Pyramids": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.090909090909092,
-                "creation_time": 1679528790.581974,
+                "steps": 499990,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499990.onnx",
+                "reward": 0.5525332689285278,
+                "creation_time": 1679532545.8988953,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499990.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 20.545454545454547,
-                "creation_time": 1679528903.4239044,
+                "steps": 999996,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999996.onnx",
+                "reward": 1.5910000056028366,
+                "creation_time": 1679533823.218424,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999996.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 22.727272727272727,
-                "creation_time": 1679529017.5858736,
+                "steps": 1000033,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000033.onnx",
+                "reward": 1.6494999900460243,
+                "creation_time": 1679533823.3661141,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
-                ]
-            },
-            {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1679529125.9976704,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1679529126.1605213,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000033.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 23.818181818181817,
-            "creation_time": 1679529126.1605213,
+            "steps": 1000033,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.6494999900460243,
+            "creation_time": 1679533823.3661141,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000033.pt"
             ]
         }
     },