Upload folder using huggingface_hub

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f6e224f79e2e1c7e66a7558ec775431bffe4e5e9c7d6b392b21384a2a6067c3
-size 1420238
+oid sha256:b8ee43d07fd878ad6e19882274ca3065a7956513b76479d83987bb85b5a95e7d
+size 1417437

Pyramids/Pyramids-499968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ee43d07fd878ad6e19882274ca3065a7956513b76479d83987bb85b5a95e7d
+size 1417437

Pyramids/Pyramids-499968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b93202bec4dc6e443f537e069c6d7e8276b69ef34977703ea0117e6eee1e06
+size 8652382

Pyramids/Pyramids-500096.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ee43d07fd878ad6e19882274ca3065a7956513b76479d83987bb85b5a95e7d
+size 1417437

Pyramids/Pyramids-500096.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd45cc82c3bc0b9a47e356b4f976401d09399bd46e49e897c512f4e01743439
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7841bf8c8c5e48b8565cc0eb38d5c026aaf63affdcb195182ccc7013975e256
-size 8655778
+oid sha256:6fd45cc82c3bc0b9a47e356b4f976401d09399bd46e49e897c512f4e01743439
+size 8652382

Pyramids/events.out.tfevents.1669238262.97cccbef8c2a.237.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733eef79a18dcc42cce06d741dbabbace07674e94eb2a92dede0c31341d73813
+size 156904

README.md

@@ -1,35 +1,31 @@
+
 ---
-library_name: ml-agents
-tags:
-- Pyramids
-- deep-reinforcement-learning
-- reinforcement-learning
-- ML-Agents-Pyramids
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-Pyramids
+      library_name: ml-agents
 ---
-
+    
   # **ppo** Agent playing **Pyramids**
-  This is a trained model of a **ppo** agent playing **Pyramids**
-  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
-
+  This is a trained model of a **ppo** agent playing **Pyramids** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+  
   ## Usage (with ML-Agents)
-  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
-
+  The Documentation: https://github.com/huggingface/ml-agents#get-started
   We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
-  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
-  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
-  - A *longer tutorial* to understand how works ML-Agents:
-  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
 
   ### Resume the training
-  ```bash
+  ```
   mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
   ```
-
   ### Watch your Agent play
-  You can watch your agent **playing directly in your browser**
-
-  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
-  2. Step 1: Find your model_id: soonchang/ML-Agents-Pyramids
+  You can watch your agent **playing directly in your browser:**.
+  
+  1. Go to https://huggingface.co/spaces/unity/ML-Agents-Pyramids
+  2. Step 1: Write your model_id: xaeroq/MLAgents-Pyramids
   3. Step 2: Select your *.nn /*.onnx file
   4. Click on Watch the agent play 👀
   

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": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-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

@@ -10,11 +10,9 @@ behaviors:
       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
@@ -50,20 +48,19 @@ behaviors:
         encoding_size: null
     init_path: null
     keep_checkpoints: 5
-    even_checkpoints: false
-    max_steps: 1000000
+    checkpoint_interval: 500000
+    max_steps: 500000
     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_path: ./trained-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
@@ -76,7 +73,6 @@ engine_settings:
   target_frame_rate: -1
   capture_frame_rate: 60
   no_graphics: true
-  no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
   run_id: Pyramids Training

run_logs/Player-0.log

@@ -1,45 +1,52 @@
-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] 55121 [Flags] 2 [Guid] 1480276777 [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] = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 172.28.0.2
+Multi-casting "[IP] 172.28.0.2 [Port] 55048 [Flags] 2 [Guid] 2268423989 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [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
 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 /content/ml-agents/trained-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
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2495:(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
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2495:(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  0.154 seconds
+- Completed reload, in  0.122 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?
@@ -61,14 +68,7 @@ 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?
-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?
-UnloadTime: 1.092951 ms
+UnloadTime: 1.334830 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.
@@ -76,7 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 3774 frames, [32.0 KB-64.0 KB]: 12053 frames, [64.0 KB-128.0 KB]: 2939 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 5087 frames, [32.0 KB-64.0 KB]: 3617 frames, [64.0 KB-128.0 KB]: 690 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
@@ -149,7 +149,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -207,29 +207,29 @@ PlayerConnection::CleanupMemory Statistics:
       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]: 18468 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9096 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 12047
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 18766 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9394 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 47.5 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 29.6 MB
+      Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 18766 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9395 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.8 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 23.7 MB
+      Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -255,15 +255,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18766 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9394 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]: 18767 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 9395 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,45 +273,45 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18468 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9096 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]: 18766 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 9394 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.5 MB
+      Peak Allocated memory 4.4 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 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18767 frames
+      Peak usage frame count: [0-1.0 KB]: 9395 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]: 18767 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9395 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]: 18767 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 9395 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 28.5 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":1703517998419,"processId":6590,"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":1669239312936,"processId":256,"allocatedMemory":1957329,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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":3444},{"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

@@ -2,249 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.3710872530937195,
-            "min": 0.35479119420051575,
-            "max": 1.5143848657608032,
-            "count": 33
+            "value": 0.6742886900901794,
+            "min": 0.6721416711807251,
+            "max": 1.3842403888702393,
+            "count": 16
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 11174.1796875,
-            "min": 10626.7060546875,
-            "max": 45940.37890625,
-            "count": 33
+            "value": 20153.140625,
+            "min": 20153.140625,
+            "max": 41992.31640625,
+            "count": 16
         },
         "Pyramids.Step.mean": {
-            "value": 989995.0,
-            "min": 29952.0,
-            "max": 989995.0,
-            "count": 33
+            "value": 479910.0,
+            "min": 29996.0,
+            "max": 479910.0,
+            "count": 16
         },
         "Pyramids.Step.sum": {
-            "value": 989995.0,
-            "min": 29952.0,
-            "max": 989995.0,
-            "count": 33
+            "value": 479910.0,
+            "min": 29996.0,
+            "max": 479910.0,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.557255744934082,
-            "min": -0.14526034891605377,
-            "max": 0.557255744934082,
-            "count": 33
+            "value": 0.0009998594177886844,
+            "min": -0.09621106088161469,
+            "max": 0.01276826485991478,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 157.1461181640625,
-            "min": -34.42670440673828,
-            "max": 157.1461181640625,
-            "count": 33
+            "value": 0.2449655532836914,
+            "min": -23.186864852905273,
+            "max": 3.038846969604492,
+            "count": 16
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.03877447172999382,
-            "min": -0.006362123414874077,
-            "max": 0.36770954728126526,
-            "count": 33
+            "value": 0.03132905438542366,
+            "min": 0.03132905438542366,
+            "max": 0.5412765741348267,
+            "count": 16
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 10.934401512145996,
-            "min": -1.7177733182907104,
-            "max": 87.14716339111328,
-            "count": 33
+            "value": 7.6756181716918945,
+            "min": 7.6756181716918945,
+            "max": 128.82382202148438,
+            "count": 16
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0672745228661808,
-            "min": 0.06501670798158611,
-            "max": 0.07346477177524312,
-            "count": 33
+            "value": 0.06983986733453897,
+            "min": 0.06526881362053823,
+            "max": 0.07415272995565701,
+            "count": 16
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9418433201265312,
-            "min": 0.4956838974572622,
-            "max": 1.0732063263179346,
-            "count": 33
+            "value": 1.0475980100180844,
+            "min": 0.5038274561005495,
+            "max": 1.0475980100180844,
+            "count": 16
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01629458488845945,
-            "min": 0.0006526181452389054,
-            "max": 0.01629458488845945,
-            "count": 33
+            "value": 0.004306636560674329,
+            "min": 0.00010371410663252939,
+            "max": 0.012851338419790715,
+            "count": 16
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.22812418843843227,
-            "min": 0.00848403588810577,
-            "max": 0.22812418843843227,
-            "count": 33
+            "value": 0.06459954841011493,
+            "min": 0.001348283386222882,
+            "max": 0.089959368938535,
+            "count": 16
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.612726033885715e-06,
-            "min": 7.612726033885715e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 2.103485298841333e-05,
+            "min": 2.103485298841333e-05,
+            "max": 0.00029047303174708567,
+            "count": 16
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010657816447440001,
-            "min": 0.00010657816447440001,
-            "max": 0.0035084789305070995,
-            "count": 33
+            "value": 0.00031552279482619997,
+            "min": 0.00031552279482619997,
+            "max": 0.003085113271629,
+            "count": 16
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10253754285714287,
-            "min": 0.10253754285714287,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10701158666666669,
+            "min": 0.10701158666666669,
+            "max": 0.19682434285714287,
+            "count": 16
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4355256,
-            "min": 1.3886848,
-            "max": 2.5694928999999997,
-            "count": 33
+            "value": 1.6051738000000002,
+            "min": 1.3777704000000002,
+            "max": 2.4221326,
+            "count": 16
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026350053142857146,
-            "min": 0.00026350053142857146,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.0007104575079999999,
+            "min": 0.0007104575079999999,
+            "max": 0.00968275185142857,
+            "count": 16
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.00368900744,
-            "min": 0.00368900744,
-            "max": 0.11697234071000001,
-            "count": 33
+            "value": 0.010656862619999999,
+            "min": 0.010656862619999999,
+            "max": 0.10286426290000002,
+            "count": 16
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.013825265690684319,
-            "min": 0.013825265690684319,
-            "max": 0.38135233521461487,
-            "count": 33
+            "value": 0.031180718913674355,
+            "min": 0.031180718913674355,
+            "max": 0.6788924932479858,
+            "count": 16
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.19355371594429016,
-            "min": 0.19355371594429016,
-            "max": 2.669466257095337,
-            "count": 33
+            "value": 0.46771079301834106,
+            "min": 0.462179571390152,
+            "max": 4.752247333526611,
+            "count": 16
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 334.0113636363636,
-            "min": 334.0113636363636,
+            "value": 900.9090909090909,
+            "min": 885.3333333333334,
             "max": 999.0,
-            "count": 33
+            "count": 16
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29393.0,
-            "min": 15984.0,
-            "max": 33057.0,
-            "count": 33
+            "value": 29730.0,
+            "min": 16667.0,
+            "max": 32430.0,
+            "count": 16
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6432522562417118,
-            "min": -1.0000000521540642,
-            "max": 1.6432522562417118,
-            "count": 33
+            "value": -0.35584853047674353,
+            "min": -0.999819407539983,
+            "max": -0.30830592771663384,
+            "count": 16
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 144.60619854927063,
-            "min": -30.46620174497366,
-            "max": 144.60619854927063,
-            "count": 33
+            "value": -11.743001505732536,
+            "min": -30.99440163373947,
+            "max": -10.482401542365551,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6432522562417118,
-            "min": -1.0000000521540642,
-            "max": 1.6432522562417118,
-            "count": 33
+            "value": -0.35584853047674353,
+            "min": -0.999819407539983,
+            "max": -0.30830592771663384,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 144.60619854927063,
-            "min": -30.46620174497366,
-            "max": 144.60619854927063,
-            "count": 33
+            "value": -11.743001505732536,
+            "min": -30.99440163373947,
+            "max": -10.482401542365551,
+            "count": 16
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.047644139063446674,
-            "min": 0.047644139063446674,
-            "max": 7.428159176371992,
-            "count": 33
+            "value": 0.2935738717699706,
+            "min": 0.2935738717699706,
+            "max": 13.230402452104231,
+            "count": 16
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 4.1926842375833075,
-            "min": 4.1926842375833075,
-            "max": 118.85054682195187,
-            "count": 33
+            "value": 9.687937768409029,
+            "min": 9.687937768409029,
+            "max": 224.91684168577194,
+            "count": 16
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 16
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 16
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1703515782",
-        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
-        "mlagents_version": "1.1.0.dev0",
-        "mlagents_envs_version": "1.1.0.dev0",
+        "start_time_seconds": "1669238253",
+        "python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
-        "pytorch_version": "2.1.2+cu121",
-        "numpy_version": "1.23.5",
-        "end_time_seconds": "1703517998"
+        "pytorch_version": "1.8.1+cu102",
+        "numpy_version": "1.21.6",
+        "end_time_seconds": "1669239313"
     },
-    "total": 2215.7548088470003,
+    "total": 1059.166157446,
     "count": 1,
-    "self": 0.4794476430006398,
+    "self": 0.44317191499999353,
     "children": {
         "run_training.setup": {
-            "total": 0.07070936500008429,
+            "total": 0.07292283600003202,
             "count": 1,
-            "self": 0.07070936500008429
+            "self": 0.07292283600003202
         },
         "TrainerController.start_learning": {
-            "total": 2215.204651839,
+            "total": 1058.6500626949999,
             "count": 1,
-            "self": 1.359752002966161,
+            "self": 0.7315944790175308,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.3331976160000067,
+                    "total": 12.279889690000005,
                     "count": 1,
-                    "self": 2.3331976160000067
+                    "self": 12.279889690000005
                 },
                 "TrainerController.advance": {
-                    "total": 2211.4257492580336,
-                    "count": 63766,
-                    "self": 1.4513701620035135,
+                    "total": 1045.5424087189824,
+                    "count": 31609,
+                    "self": 0.8037784609789469,
                     "children": {
                         "env_step": {
-                            "total": 1570.8221303140824,
-                            "count": 63766,
-                            "self": 1436.3440708690725,
+                            "total": 671.1690453100025,
+                            "count": 31609,
+                            "self": 613.3330664429438,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 133.61226920101285,
-                                    "count": 63766,
-                                    "self": 4.84103026803723,
+                                    "total": 57.42272636403999,
+                                    "count": 31609,
+                                    "self": 2.4958523180122256,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 128.77123893297562,
-                                            "count": 62554,
-                                            "self": 128.77123893297562
+                                            "total": 54.92687404602776,
+                                            "count": 31316,
+                                            "self": 18.69540972801883,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 36.23146431800893,
+                                                    "count": 31316,
+                                                    "self": 36.23146431800893
+                                                }
+                                            }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8657902439970258,
-                                    "count": 63766,
+                                    "total": 0.4132525030187253,
+                                    "count": 31609,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2209.7449179168934,
-                                            "count": 63766,
+                                            "total": 1056.0520628660086,
+                                            "count": 31609,
                                             "is_parallel": true,
-                                            "self": 896.1744166428964,
+                                            "self": 499.2166750820163,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0017345950000162702,
+                                                            "total": 0.005752630000017689,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005544049997752154,
+                                                            "self": 0.004342835000102241,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0011801900002410548,
+                                                                    "total": 0.001409794999915448,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0011801900002410548
+                                                                    "self": 0.001409794999915448
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05237587900001017,
+                                                            "total": 0.04728041300000996,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006416359999548149,
+                                                            "self": 0.0005680020000795594,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005207960000461753,
+                                                                    "total": 0.00044893799997680617,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005207960000461753
+                                                                    "self": 0.00044893799997680617
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04948841400005222,
+                                                                    "total": 0.04443254099999194,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04948841400005222
+                                                                    "self": 0.04443254099999194
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017250329999569658,
+                                                                    "total": 0.0018309319999616491,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000370162000081109,
+                                                                    "self": 0.0004831749999425483,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013548709998758568,
+                                                                            "total": 0.0013477570000191008,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013548709998758568
+                                                                            "self": 0.0013477570000191008
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1313.570501273997,
-                                                    "count": 63765,
+                                                    "total": 556.8353877839922,
+                                                    "count": 31608,
                                                     "is_parallel": true,
-                                                    "self": 34.69091422898123,
+                                                    "self": 14.482318291993124,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 25.305957065010944,
-                                                            "count": 63765,
+                                                            "total": 13.095371672995725,
+                                                            "count": 31608,
                                                             "is_parallel": true,
-                                                            "self": 25.305957065010944
+                                                            "self": 13.095371672995725
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1152.4164550949642,
-                                                            "count": 63765,
+                                                            "total": 479.25650388000355,
+                                                            "count": 31608,
                                                             "is_parallel": true,
-                                                            "self": 1152.4164550949642
+                                                            "self": 479.25650388000355
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 101.1571748850406,
-                                                            "count": 63765,
+                                                            "total": 50.001193938999904,
+                                                            "count": 31608,
                                                             "is_parallel": true,
-                                                            "self": 20.606153722172394,
+                                                            "self": 12.548865062003244,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 80.55102116286821,
-                                                                    "count": 510120,
+                                                                    "total": 37.45232887699666,
+                                                                    "count": 252864,
                                                                     "is_parallel": true,
-                                                                    "self": 80.55102116286821
+                                                                    "self": 37.45232887699666
                                                                 }
                                                             }
                                                         }
@@ -343,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 639.152248781948,
-                            "count": 63766,
-                            "self": 2.610875363061041,
+                            "total": 373.5695849480011,
+                            "count": 31609,
+                            "self": 1.2859233069930838,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 128.0266002138983,
-                                    "count": 63766,
-                                    "self": 127.8289334128981,
+                                    "total": 88.0393692000078,
+                                    "count": 31609,
+                                    "self": 87.81661983700775,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.19766680100019585,
-                                            "count": 2,
-                                            "self": 0.19766680100019585
+                                            "total": 0.2227493630000481,
+                                            "count": 1,
+                                            "self": 0.2227493630000481
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 508.5147732049886,
-                                    "count": 450,
-                                    "self": 305.11276038298047,
+                                    "total": 284.2442924410002,
+                                    "count": 219,
+                                    "self": 111.21688866898762,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 203.40201282200815,
-                                            "count": 22803,
-                                            "self": 203.40201282200815
+                                            "total": 173.02740377201258,
+                                            "count": 11415,
+                                            "self": 173.02740377201258
                                         }
                                     }
                                 }
@@ -376,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.61000296229031e-07,
+                    "total": 1.3049998415226582e-06,
                     "count": 1,
-                    "self": 9.61000296229031e-07
+                    "self": 1.3049998415226582e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08595200099989597,
+                    "total": 0.09616850199995497,
                     "count": 1,
-                    "self": 0.0016194410000025528,
+                    "self": 0.0016773950001152116,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08433255999989342,
+                            "total": 0.09449110699983976,
                             "count": 1,
-                            "self": 0.08433255999989342
+                            "self": 0.09449110699983976
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,46 +2,37 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499922,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499922.onnx",
-                "reward": null,
-                "creation_time": 1703516808.0753455,
+                "steps": 499968,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499968.onnx",
+                "reward": -0.9994000494480133,
+                "creation_time": 1669239312.4448318,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499922.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499968.pt"
                 ]
             },
             {
-                "steps": 999963,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999963.onnx",
-                "reward": 1.7571666464209557,
-                "creation_time": 1703517997.8967001,
+                "steps": 500096,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500096.onnx",
+                "reward": -0.9994000494480133,
+                "creation_time": 1669239312.5632164,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999963.pt"
-                ]
-            },
-            {
-                "steps": 1000091,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000091.onnx",
-                "reward": 1.7571666464209557,
-                "creation_time": 1703517997.9944656,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000091.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-500096.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000091,
+            "steps": 500096,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7571666464209557,
-            "creation_time": 1703517997.9944656,
+            "reward": -0.9994000494480133,
+            "creation_time": 1669239312.5632164,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000091.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-500096.pt"
             ]
         }
     },
     "metadata": {
         "stats_format_version": "0.3.0",
-        "mlagents_version": "1.1.0.dev0",
-        "torch_version": "2.1.2+cu121"
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1+cu102"
     }
 }