First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b71ed4630275113a26e524a3618d00974443c674521a436c0f0b775f24908216
+oid sha256:66a038497b95e5ea273310005ab07c7469436f1cc7b512bacff3212d5361229a
 size 1420238

Pyramids/Pyramids-1499963.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f242c86054a6f8143b92fdd86282353b0bf75ff8316a6c36f52ea1649825c76d
+size 1420238

Pyramids/Pyramids-1499963.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0f8e26c56c879803bbd32659b1ece9b85ff9aeb55b610e5177ba9a0f423ad3
+size 8942939

Pyramids/Pyramids-1999875.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:943d2359d9e2175b0b424f699a972340c30c99175cac61d3d5cad466a59a02a1
+size 1420238

Pyramids/Pyramids-1999875.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ff7fe50f6f8ccb48259dc15eccec737b39b7f88b5f883babc0dbf07aa7ee67
+size 8942939

Pyramids/Pyramids-2499942.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da1a9312c96a2039c7dc5a64ab1aa67837c46e8272c7b82a19b2aa800cfd1ee
+size 1420238

Pyramids/Pyramids-2499942.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86873552cf519488e6a17d645e25ef1ad5d70fa4f2cc302f5b8fa8ce273b2054
+size 8942939

Pyramids/Pyramids-2999889.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a038497b95e5ea273310005ab07c7469436f1cc7b512bacff3212d5361229a
+size 1420238

Pyramids/Pyramids-2999889.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb7e406fecf01fbc2b8af763f3976a0dcbbace54158d0c4dff563bf073c3963
+size 8942939

Pyramids/Pyramids-3000017.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a038497b95e5ea273310005ab07c7469436f1cc7b512bacff3212d5361229a
+size 1420238

Pyramids/Pyramids-3000017.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1338ad51eea2ae6aa68c3f9e12ecb7cae995bd4866aaff5146aa50a9ccb2300
+size 8942939

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39d877c24048e6c7371fc675734e385ba1b4b9df9c3c7d294276cd1512e51606
-size 8656181
+oid sha256:a2692179afd93b5f7a4e784f7b1471d4a34c6bf728790d6be7558a53d873e3a2
+size 8942389

Pyramids/events.out.tfevents.1756807880.hungchan-Precision-7560.12651.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75007aac9bfa568ab4826adf3f08d1abc1c01cbb136fa6ccfc1c8206977a19c6
+size 998825

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 5120, "learning_rate": 0.0001, "beta": 0.015, "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": 0.995, "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": 0.1, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "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 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

@@ -3,10 +3,10 @@ behaviors:
   Pyramids:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 2048
-      learning_rate: 0.0003
-      beta: 0.01
+      batch_size: 512
+      buffer_size: 5120
+      learning_rate: 0.0001
+      beta: 0.015
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -25,7 +25,7 @@ behaviors:
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.99
+        gamma: 0.995
         strength: 1.0
         network_settings:
           normalize: false
@@ -37,21 +37,21 @@ behaviors:
           deterministic: false
       rnd:
         gamma: 0.99
-        strength: 0.01
+        strength: 0.1
         network_settings:
           normalize: false
-          hidden_units: 64
+          hidden_units: 128
           num_layers: 3
           vis_encode_type: simple
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-        learning_rate: 0.0001
+        learning_rate: 0.0003
         encoding_size: null
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,42 +1,22 @@
-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] 55034 [Flags] 2 [Guid] 1450271860 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Mono path[0] = '/media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 192.168.1.10
+Multi-casting "[IP] 192.168.1.10 [Port] 55360 [Flags] 2 [Guid] 1862415126 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.10) [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/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
+PlayerPrefs - Creating folder: /home/hungchan/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/hungchan/.config/unity3d/Unity Technologies/UnityEnvironment
 Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
-[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+[Subsystems] Discovering subsystems at path /media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
     Version:  NULL 1.0 [1.0]
     Renderer: Null Device
     Vendor:   Unity Technologies
-ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
-ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
-ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
-ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
-ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
-FMOD failed to initialize the output device.: "Error initializing output device. " (60)
-Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
-ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
-ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
-ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
-ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
-ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
-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  0.087 seconds
+- Completed reload, in  0.060 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)
@@ -68,19 +48,24 @@ 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: 0.759157 ms
+UnloadTime: 0.531279 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.
+Setting up 8 worker threads for Enlighten.
 PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 3181 frames, [32.0 KB-64.0 KB]: 12513 frames, [64.0 KB-128.0 KB]: 3073 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 15753 frames, [32.0 KB-64.0 KB]: 30116 frames, [64.0 KB-128.0 KB]: 10403 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_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 1.9 KB
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -91,16 +76,16 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [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_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
@@ -126,37 +111,72 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 7]
+    [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 15]
+    [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_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
       Current Block Size 320.0 KB
-      Peak Allocated Bytes 251.5 KB
+      Peak Allocated Bytes 251.6 KB
       Overflow Count 4
-    [ALLOC_TEMP_Profiler.Dispatcher]
+    [ALLOC_TEMP_AUDIO_FMOD PulseAudio Mixer]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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
       Overflow Count 0
-    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 15
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -171,11 +191,21 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      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 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -184,7 +214,17 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
@@ -196,39 +236,49 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker]
+    [ALLOC_TEMP_EnlightenWorker] x 8
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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
+      Peak Allocated Bytes 159 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18469 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55974 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 12983
+  Peak main deferred allocation count 12580
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18767 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56271 frames, [32.0 MB-64.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 29.9 MB
+      Peak Allocated memory 32.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18768 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56273 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.3 MB
+      Peak Allocated memory 27.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +307,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18767 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56272 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18768 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 56273 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +325,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18469 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55974 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 18767 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 56272 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -293,25 +343,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18768 frames
+      Peak usage frame count: [0-1.0 KB]: 56273 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]: 18768 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56273 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18768 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 56273 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 38.0 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":1756521496443,"processId":14189,"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}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1756811134930,"processId":12700,"allocatedMemory":2044915,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":73418},{"Thread":34852},{"Manager":18447},{"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":3664},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.2851555645465851,
-            "min": 0.2782154083251953,
-            "max": 1.4448691606521606,
-            "count": 33
+            "value": 0.3648880124092102,
+            "min": 0.3586031198501587,
+            "max": 1.5152931213378906,
+            "count": 100
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 8504.4794921875,
-            "min": 8279.6904296875,
-            "max": 43831.55078125,
-            "count": 33
+            "value": 10993.345703125,
+            "min": 10647.3603515625,
+            "max": 45967.93359375,
+            "count": 100
         },
         "Pyramids.Step.mean": {
-            "value": 989999.0,
+            "value": 2999889.0,
             "min": 29952.0,
-            "max": 989999.0,
-            "count": 33
+            "max": 2999889.0,
+            "count": 100
         },
         "Pyramids.Step.sum": {
-            "value": 989999.0,
+            "value": 2999889.0,
             "min": 29952.0,
-            "max": 989999.0,
-            "count": 33
+            "max": 2999889.0,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5550706386566162,
-            "min": -0.09250201284885406,
-            "max": 0.5713458061218262,
-            "count": 33
+            "value": 0.4423373341560364,
+            "min": -0.15380437672138214,
+            "max": 0.9697663187980652,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 154.86471557617188,
-            "min": -22.065343856811523,
-            "max": 158.83413696289062,
-            "count": 33
+            "value": 114.12303161621094,
+            "min": -37.066856384277344,
+            "max": 275.41363525390625,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.01356449630111456,
-            "min": -0.005851727910339832,
-            "max": 0.3740640878677368,
-            "count": 33
+            "value": -0.07140153646469116,
+            "min": -0.961536705493927,
+            "max": 5.297674655914307,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 3.784494400024414,
-            "min": -1.555336356163025,
-            "max": 89.77538299560547,
-            "count": 33
+            "value": -18.42159652709961,
+            "min": -265.3841247558594,
+            "max": 1271.44189453125,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06786125359487617,
-            "min": 0.0646033263587147,
-            "max": 0.07348613034645539,
-            "count": 33
+            "value": 0.02993082449150582,
+            "min": 0.02849066569987271,
+            "max": 0.03923334629243155,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.0179188039231426,
-            "min": 0.48325549620076547,
-            "max": 1.099867147684563,
-            "count": 33
+            "value": 0.17958494694903493,
+            "min": 0.14626130897862216,
+            "max": 0.23087790133431554,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01752096807661777,
-            "min": 0.0010791649419158791,
-            "max": 0.01752096807661777,
-            "count": 33
+            "value": 0.03069851579558518,
+            "min": 0.002553138680781962,
+            "max": 3.253386940026299,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.2628145211492665,
-            "min": 0.00870653271248421,
-            "max": 0.2628145211492665,
-            "count": 33
+            "value": 0.1841910947735111,
+            "min": 0.015318832084691772,
+            "max": 13.013547760105196,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.437677520806665e-06,
-            "min": 7.437677520806665e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 5.28643915900003e-07,
+            "min": 5.28643915900003e-07,
+            "max": 9.94944005056e-05,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00011156516281209998,
-            "min": 0.00011156516281209998,
-            "max": 0.0033841898719368002,
-            "count": 33
+            "value": 3.171863495400018e-06,
+            "min": 3.171863495400018e-06,
+            "max": 0.0005790079209921001,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10247919333333333,
-            "min": 0.10247919333333333,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10052854444444446,
+            "min": 0.10052854444444446,
+            "max": 0.19949440000000002,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.5371879,
-            "min": 1.3691136000000002,
-            "max": 2.5726429,
-            "count": 33
+            "value": 0.6031712666666668,
+            "min": 0.5073915,
+            "max": 1.1790079000000002,
+            "count": 100
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.000257671414,
-            "min": 0.000257671414,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 8.922881222222263e-05,
+            "min": 8.922881222222263e-05,
+            "max": 0.01492421056,
+            "count": 100
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.00386507121,
-            "min": 0.00386507121,
-            "max": 0.11283351368000001,
-            "count": 33
+            "value": 0.0005353728733333358,
+            "min": 0.0005353728733333358,
+            "max": 0.08685328420999999,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.018648721277713776,
-            "min": 0.018648721277713776,
-            "max": 0.49155110120773315,
-            "count": 33
+            "value": 0.020344262942671776,
+            "min": 0.019488167017698288,
+            "max": 0.8116133213043213,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.27973082661628723,
-            "min": 0.26454275846481323,
-            "max": 3.4408576488494873,
-            "count": 33
+            "value": 0.12206558138132095,
+            "min": 0.09929914772510529,
+            "max": 3.246453285217285,
+            "count": 100
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 325.6,
-            "min": 325.6,
+            "value": 515.0714285714286,
+            "min": 282.6504854368932,
             "max": 999.0,
-            "count": 33
+            "count": 100
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29304.0,
+            "value": 28844.0,
             "min": 15984.0,
-            "max": 32305.0,
-            "count": 33
+            "max": 32957.0,
+            "count": 100
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.5632599766055744,
+            "value": 1.0562321172494973,
             "min": -1.0000000521540642,
-            "max": 1.6190045269375497,
-            "count": 33
+            "max": 1.7068762734685976,
+            "count": 100
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 140.6933978945017,
+            "value": 59.14899856597185,
             "min": -32.000001668930054,
-            "max": 143.7947978824377,
-            "count": 33
+            "max": 174.88659876585007,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.5632599766055744,
+            "value": 1.0562321172494973,
             "min": -1.0000000521540642,
-            "max": 1.6190045269375497,
-            "count": 33
+            "max": 1.7068762734685976,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 140.6933978945017,
+            "value": 59.14899856597185,
             "min": -32.000001668930054,
-            "max": 143.7947978824377,
-            "count": 33
+            "max": 174.88659876585007,
+            "count": 100
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.06308855150394568,
-            "min": 0.06308855150394568,
-            "max": 9.597885727882385,
-            "count": 33
+            "value": 1.0782365690683946,
+            "min": 0.6000466791741116,
+            "max": 186.66918002068996,
+            "count": 100
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 5.677969635355112,
-            "min": 5.677969635355112,
-            "max": 153.56617164611816,
-            "count": 33
+            "value": 60.3812478678301,
+            "min": 57.350965306162834,
+            "max": 2986.7068803310394,
+            "count": 100
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 100
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 100
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1756519402",
-        "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
-        "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",
+        "start_time_seconds": "1756807880",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/hungchan/miniconda3/envs/rl_31012/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1756521496"
+        "end_time_seconds": "1756811134"
     },
-    "total": 2093.5394558969997,
+    "total": 3254.906885005,
     "count": 1,
-    "self": 0.43008636399963507,
+    "self": 0.2768450399998983,
     "children": {
         "run_training.setup": {
-            "total": 0.02024385100003201,
+            "total": 0.0508246000000554,
             "count": 1,
-            "self": 0.02024385100003201
+            "self": 0.0508246000000554
         },
         "TrainerController.start_learning": {
-            "total": 2093.089125682,
+            "total": 3254.579215365,
             "count": 1,
-            "self": 1.1642944240384168,
+            "self": 3.9781296309993195,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.0109279920002336,
+                    "total": 1.6173410069999363,
                     "count": 1,
-                    "self": 2.0109279920002336
+                    "self": 1.6173410069999363
                 },
                 "TrainerController.advance": {
-                    "total": 2089.839375633961,
-                    "count": 63901,
-                    "self": 1.2338740388831866,
+                    "total": 3248.9333752689995,
+                    "count": 192208,
+                    "self": 3.8575478021493836,
                     "children": {
                         "env_step": {
-                            "total": 1455.9357925541717,
-                            "count": 63901,
-                            "self": 1318.1331074631826,
+                            "total": 2403.0913357258564,
+                            "count": 192208,
+                            "self": 2043.4582030849242,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 137.06486186191023,
-                                    "count": 63901,
-                                    "self": 4.410685361944161,
+                                    "total": 356.9428961030411,
+                                    "count": 192208,
+                                    "self": 10.942023073978817,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 132.65417649996607,
-                                            "count": 62559,
-                                            "self": 132.65417649996607
+                                            "total": 346.0008730290623,
+                                            "count": 187576,
+                                            "self": 346.0008730290623
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7378232290789128,
-                                    "count": 63901,
+                                    "total": 2.6902365378909963,
+                                    "count": 192208,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2088.9097545370905,
-                                            "count": 63901,
+                                            "total": 3249.4381485699073,
+                                            "count": 192208,
                                             "is_parallel": true,
-                                            "self": 873.7015860120046,
+                                            "self": 1447.6441811618483,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0018327879997741547,
+                                                            "total": 0.0015645739999854413,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005426249990705401,
+                                                            "self": 0.0006215849999762213,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012901630007036147,
+                                                                    "total": 0.00094298900000922,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012901630007036147
+                                                                    "self": 0.00094298900000922
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.046699727000032,
+                                                            "total": 0.022063921000039954,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005188389995964826,
+                                                            "self": 0.0003220639999881314,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044619700020120945,
+                                                                    "total": 0.00025572000004103757,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044619700020120945
+                                                                    "self": 0.00025572000004103757
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.043961182000202825,
+                                                                    "total": 0.020777554000005694,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.043961182000202825
+                                                                    "self": 0.020777554000005694
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017735090000314813,
+                                                                    "total": 0.0007085830000050919,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004289010003049043,
+                                                                    "self": 0.00016922600025282009,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001344607999726577,
+                                                                            "total": 0.0005393569997522718,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001344607999726577
+                                                                            "self": 0.0005393569997522718
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1215.208168525086,
-                                                    "count": 63900,
+                                                    "total": 1801.793967408059,
+                                                    "count": 192207,
                                                     "is_parallel": true,
-                                                    "self": 30.523771564255185,
+                                                    "self": 48.72282670608752,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.073354882970307,
-                                                            "count": 63900,
+                                                            "total": 34.8379522510445,
+                                                            "count": 192207,
                                                             "is_parallel": true,
-                                                            "self": 22.073354882970307
+                                                            "self": 34.8379522510445
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1069.8048236229279,
-                                                            "count": 63900,
+                                                            "total": 1585.4346769339122,
+                                                            "count": 192207,
                                                             "is_parallel": true,
-                                                            "self": 1069.8048236229279
+                                                            "self": 1585.4346769339122
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 92.8062184549326,
-                                                            "count": 63900,
+                                                            "total": 132.79851151701473,
+                                                            "count": 192207,
                                                             "is_parallel": true,
-                                                            "self": 18.563303370328867,
+                                                            "self": 30.497360784974717,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 74.24291508460374,
-                                                                    "count": 511200,
+                                                                    "total": 102.30115073204001,
+                                                                    "count": 1537656,
                                                                     "is_parallel": true,
-                                                                    "self": 74.24291508460374
+                                                                    "self": 102.30115073204001
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 632.6697090409061,
-                            "count": 63901,
-                            "self": 2.2547354159410133,
+                            "total": 841.9844917409937,
+                            "count": 192208,
+                            "self": 7.850889706003613,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 117.36929369796553,
-                                    "count": 63901,
-                                    "self": 117.19345990996544,
+                                    "total": 243.33867124098867,
+                                    "count": 192208,
+                                    "self": 242.87500665398795,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.17583378800009086,
-                                            "count": 2,
-                                            "self": 0.17583378800009086
+                                            "total": 0.46366458700072144,
+                                            "count": 6,
+                                            "self": 0.46366458700072144
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 513.0456799269996,
-                                    "count": 447,
-                                    "self": 286.35968652991414,
+                                    "total": 590.7949307940014,
+                                    "count": 571,
+                                    "self": 449.5698461020147,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 226.68599339708544,
-                                            "count": 22788,
-                                            "self": 226.68599339708544
+                                            "total": 141.2250846919867,
+                                            "count": 17277,
+                                            "self": 141.2250846919867
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.470004442846403e-07,
+                    "total": 9.10000380827114e-07,
                     "count": 1,
-                    "self": 9.470004442846403e-07
+                    "self": 9.10000380827114e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07452668499990978,
+                    "total": 0.050368548000733426,
                     "count": 1,
-                    "self": 0.0012463780003599823,
+                    "self": 0.0009564040001350804,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.0732803069995498,
+                            "total": 0.049412144000598346,
                             "count": 1,
-                            "self": 0.0732803069995498
+                            "self": 0.049412144000598346
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499983,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499983.onnx",
-                "reward": 1.714999943971634,
-                "creation_time": 1756520369.193977,
+                "steps": 1499963,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499963.onnx",
+                "reward": 1.7101666182279587,
+                "creation_time": 1756809478.994942,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499983.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499963.pt"
                 ]
             },
             {
-                "steps": 999885,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999885.onnx",
-                "reward": 1.8151999861001968,
-                "creation_time": 1756521495.9515636,
+                "steps": 1999875,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999875.onnx",
+                "reward": 1.6790833187599976,
+                "creation_time": 1756810023.7486002,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999885.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1999875.pt"
                 ]
             },
             {
-                "steps": 1000013,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000013.onnx",
-                "reward": 1.8151999861001968,
-                "creation_time": 1756521496.0362542,
+                "steps": 2499942,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499942.onnx",
+                "reward": 1.6999999582767487,
+                "creation_time": 1756810576.229811,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000013.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2499942.pt"
+                ]
+            },
+            {
+                "steps": 2999889,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999889.onnx",
+                "reward": -0.999800056219101,
+                "creation_time": 1756811134.6330178,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999889.pt"
+                ]
+            },
+            {
+                "steps": 3000017,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000017.onnx",
+                "reward": -0.999800056219101,
+                "creation_time": 1756811134.6921918,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000017.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000013,
+            "steps": 3000017,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.8151999861001968,
-            "creation_time": 1756521496.0362542,
+            "reward": -0.999800056219101,
+            "creation_time": 1756811134.6921918,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000013.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000017.pt"
             ]
         }
     },