Trained Pyramids agent upload

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8902a6c2685434bbc69e8dc4a7247469e9953293e175415cbbab0ee8dc622bed
+size 1418184

Pyramids/Pyramids-1000111.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8902a6c2685434bbc69e8dc4a7247469e9953293e175415cbbab0ee8dc622bed
+size 1418184

Pyramids/Pyramids-1000111.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fc5e373f3842f82dbcf9c3fe68ddf0e22043be0b224871dabd33e7f7bf3122
+size 8650158

Pyramids/Pyramids-499877.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bdc0ed52fac2099189f14b4b83398effba03bad8115db82625bf2deb00f2da
+size 1418184

Pyramids/Pyramids-499877.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3e8852d2c1051c7c53647cbba572231f0a207f20a638b0e9cc171dfc4f6d18
+size 8650158

Pyramids/Pyramids-999983.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8902a6c2685434bbc69e8dc4a7247469e9953293e175415cbbab0ee8dc622bed
+size 1418184

Pyramids/Pyramids-999983.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b293e67284482b48f6a33ec1f6a0b1b5ade3389e39148f40ee68d8fbce543a4f
+size 8650158

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fc5e373f3842f82dbcf9c3fe68ddf0e22043be0b224871dabd33e7f7bf3122
+size 8650158

Pyramids/events.out.tfevents.1655887488.Thomas.23228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70f980895bf58f392b333458f35ae3526c441bd032ef4ded99c9164aaf2b4d2
+size 323504

README.md

@@ -0,0 +1,31 @@
+
+---
+      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).
+  
+  ## Usage (with ML-Agents)
+  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:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/Unity-ML-Agents-Pyramids
+  2. Step 1: Write your model_id: ThomasSimonini/MLAgents-Pyramids
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +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, "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": 0.02, "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": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables/windows/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": "First 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

@@ -0,0 +1,88 @@
+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: 0.02
+        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: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: training-envs-executables/windows/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: First 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

run_logs/Player-0.log

@@ -0,0 +1,79 @@
+Mono path[0] = 'C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Managed'
+Mono config path = 'C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/MonoBleedingEdge/etc'
+PlayerConnection initialized from C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data (debug = 0)
+PlayerConnection initialized network socket : 0.0.0.0 55418
+Multi-casting "[IP] 192.168.12.119 [Port] 55418 [Flags] 2 [Guid] 184333026 [EditorId] 2673693869 [Version] 1048832 [Id] WindowsPlayer(Thomas) [Debug] 0 [PackageName] WindowsPlayer [ProjectName] Pyramids" to [225.0.0.222:54997]...
+Started listening to [0.0.0.0:55418]
+PlayerConnection already initialized - listening to [0.0.0.0:55418]
+Initialize engine version: 2020.3.30f1 (1fb1bf06830e)
+[Subsystems] Discovering subsystems at path C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.099 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: '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?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.755100 ms
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libcoreclr.so
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libcoreclr.so.dll
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libcoreclr.so
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libdl.so
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libdl.so.dll
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libdl.so
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libSystem.dylib
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libSystem.dylib.dll
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libSystem.dylib
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libcoreclr.so
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libcoreclr.so.dll
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libcoreclr.so
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libdl.so
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libdl.so.dll
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libdl.so
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libSystem.dylib
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libSystem.dylib.dll
+Fallback handler could not load library C:/Users/simon/OneDrive/Documents/deletetonight/ml-agents/training-envs-executables/windows/Pyramids/Pyramids_Data/Mono/libSystem.dylib
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 8 worker threads for Enlighten.
+  Thread -> id: 65c8 -> priority: 1 
+  Thread -> id: cb4 -> priority: 1 
+  Thread -> id: 5dd8 -> priority: 1 
+  Thread -> id: 3498 -> priority: 1 
+  Thread -> id: 6174 -> priority: 1 
+  Thread -> id: 6004 -> priority: 1 
+  Thread -> id: 3708 -> priority: 1 
+  Thread -> id: 1df4 -> priority: 1 
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1655889610157,"processId":19244,"allocatedMemory":7787,"memoryLabels":[{"Permanent":40},{"NewDelete":280},{"Thread":72},{"Manager":1872},{"Shader":1280},{"GfxDevice":72},{"Serialization":40},{"WebCam":32},{"String":555},{"HashMap":1536},{"PoolAlloc":56},{"GI":296},{"VR":1560},{"Subsystems":96}]}

run_logs/timers.json

@@ -0,0 +1,363 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.3135221004486084,
+            "min": 0.3080785870552063,
+            "max": 1.3124607801437378,
+            "count": 33
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 9390.6142578125,
+            "min": 9296.5791015625,
+            "max": 39814.80859375,
+            "count": 33
+        },
+        "Pyramids.Step.mean": {
+            "value": 989943.0,
+            "min": 29952.0,
+            "max": 989943.0,
+            "count": 33
+        },
+        "Pyramids.Step.sum": {
+            "value": 989943.0,
+            "min": 29952.0,
+            "max": 989943.0,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.6107106804847717,
+            "min": -0.08106255531311035,
+            "max": 0.7531508803367615,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 172.2204132080078,
+            "min": -19.617137908935547,
+            "max": 219.92005920410156,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.004609628114849329,
+            "min": 0.004609628114849329,
+            "max": 0.798308789730072,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 1.299915075302124,
+            "min": 1.299915075302124,
+            "max": 189.19918823242188,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.0673396650423196,
+            "min": 0.06628346351681273,
+            "max": 0.0738899672235244,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9427553105924744,
+            "min": 0.5037647476735934,
+            "max": 1.07743569652381,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015478121448333175,
+            "min": 0.0009254999552633766,
+            "max": 0.02462924714090282,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21669370027666446,
+            "min": 0.012031499418423896,
+            "max": 0.21702290107564562,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.658304590121429e-06,
+            "min": 7.658304590121429e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.0001072162642617,
+            "min": 0.0001072162642617,
+            "max": 0.0033710305763231994,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10255273571428572,
+            "min": 0.10255273571428572,
+            "max": 0.19838354285714285,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4357383000000001,
+            "min": 1.3886848,
+            "max": 2.5724042000000003,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0002650182978571429,
+            "min": 0.0002650182978571429,
+            "max": 0.00983851593142857,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.003710256170000001,
+            "min": 0.003710256170000001,
+            "max": 0.11238531232,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.012394525110721588,
+            "min": 0.012394525110721588,
+            "max": 0.5195097923278809,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.17352335155010223,
+            "min": 0.17352335155010223,
+            "max": 3.636568546295166,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 318.8191489361702,
+            "min": 268.8125,
+            "max": 999.0,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29969.0,
+            "min": 15984.0,
+            "max": 33007.0,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6173404060462688,
+            "min": -1.0000000521540642,
+            "max": 1.7313893662881008,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 152.02999816834927,
+            "min": -30.69900171458721,
+            "max": 195.64699839055538,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6173404060462688,
+            "min": -1.0000000521540642,
+            "max": 1.7313893662881008,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 152.02999816834927,
+            "min": -30.69900171458721,
+            "max": 195.64699839055538,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.08165901292631268,
+            "min": 0.07084223590801528,
+            "max": 21.35120641812682,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 7.675947215073393,
+            "min": 7.675947215073393,
+            "max": 341.61930269002914,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1655887485",
+        "python_version": "3.8.13 (default, Mar 28 2022, 06:59:08) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\simon\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn config/ppo/PyramidsRND.yaml --env=training-envs-executables/windows/Pyramids --run-id=First Training --no-graphics",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cpu",
+        "numpy_version": "1.22.3",
+        "end_time_seconds": "1655889610"
+    },
+    "total": 2124.2172705,
+    "count": 1,
+    "self": 0.33972799999992276,
+    "children": {
+        "run_training.setup": {
+            "total": 0.10456939999999992,
+            "count": 1,
+            "self": 0.10456939999999992
+        },
+        "TrainerController.start_learning": {
+            "total": 2123.7729731,
+            "count": 1,
+            "self": 1.4972784000137835,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.5432875000000004,
+                    "count": 1,
+                    "self": 2.5432875000000004
+                },
+                "TrainerController.advance": {
+                    "total": 2119.637074799986,
+                    "count": 63922,
+                    "self": 1.3389061000143556,
+                    "children": {
+                        "env_step": {
+                            "total": 1002.009181799981,
+                            "count": 63922,
+                            "self": 914.5827900999385,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 86.43811320004502,
+                                    "count": 63922,
+                                    "self": 4.581756500062625,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 81.8563566999824,
+                                            "count": 62562,
+                                            "self": 17.661204599972166,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 64.19515210001023,
+                                                    "count": 62562,
+                                                    "self": 64.19515210001023
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.9882784999974925,
+                                    "count": 63922,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2118.8259228000197,
+                                            "count": 63922,
+                                            "is_parallel": true,
+                                            "self": 1317.0071946000226,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.003038200000000213,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.000812000000000701,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.002226199999999512,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.002226199999999512
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 801.8156899999972,
+                                                    "count": 63922,
+                                                    "is_parallel": true,
+                                                    "self": 24.276597200004858,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 22.603133900009503,
+                                                            "count": 63922,
+                                                            "is_parallel": true,
+                                                            "self": 22.603133900009503
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 684.1701527999991,
+                                                            "count": 63922,
+                                                            "is_parallel": true,
+                                                            "self": 684.1701527999991
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 70.76580609998366,
+                                                            "count": 63922,
+                                                            "is_parallel": true,
+                                                            "self": 16.251438199991085,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 54.51436789999258,
+                                                                    "count": 511376,
+                                                                    "is_parallel": true,
+                                                                    "self": 54.51436789999258
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1116.2889868999905,
+                            "count": 63922,
+                            "self": 2.6867007000005287,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 271.42028409998926,
+                                    "count": 63922,
+                                    "self": 271.0934065999891,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.32687750000013693,
+                                            "count": 2,
+                                            "self": 0.32687750000013693
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 842.1820021000008,
+                                    "count": 451,
+                                    "self": 279.3468746999954,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 562.8351274000054,
+                                            "count": 22797,
+                                            "self": 562.8351274000054
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.000001798791345e-07,
+                    "count": 1,
+                    "self": 8.000001798791345e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09533160000000862,
+                    "count": 1,
+                    "self": 0.002389300000231742,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.09294229999977688,
+                            "count": 1,
+                            "self": 0.09294229999977688
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499877,
+                "file_path": "results\\First Training\\Pyramids\\Pyramids-499877.onnx",
+                "reward": 1.5509999245405197,
+                "creation_time": 1655888583.8329303,
+                "auxillary_file_paths": [
+                    "results\\First Training\\Pyramids\\Pyramids-499877.pt"
+                ]
+            },
+            {
+                "steps": 999983,
+                "file_path": "results\\First Training\\Pyramids\\Pyramids-999983.onnx",
+                "reward": 1.6339999735355377,
+                "creation_time": 1655889609.7258599,
+                "auxillary_file_paths": [
+                    "results\\First Training\\Pyramids\\Pyramids-999983.pt"
+                ]
+            },
+            {
+                "steps": 1000111,
+                "file_path": "results\\First Training\\Pyramids\\Pyramids-1000111.onnx",
+                "reward": 1.6339999735355377,
+                "creation_time": 1655889609.8388586,
+                "auxillary_file_paths": [
+                    "results\\First Training\\Pyramids\\Pyramids-1000111.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000111,
+            "file_path": "results\\First Training\\Pyramids.onnx",
+            "reward": 1.6339999735355377,
+            "creation_time": 1655889609.8388586,
+            "auxillary_file_paths": [
+                "results\\First Training\\Pyramids\\Pyramids-1000111.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.11.0+cpu"
+    }
+}