Final PPO + Curiosity model trained for 10M steps using Optuna best parameters

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b88ac4622db45d719d7aedd91ac4d4e26e23009c3f8f59c964dfda1f029ab6
+size 1420238

Pyramids/Pyramids-10000092.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b88ac4622db45d719d7aedd91ac4d4e26e23009c3f8f59c964dfda1f029ab6
+size 1420238

Pyramids/Pyramids-10000092.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88e8c472fe71123e8fa8332906e954fb2e04741f856d572f876cea0a7a68f05
+size 10002540

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7b6d710bc7b031b036d3271dfadf646f59de2311e208610b0db2b4814f5fde
+size 10001973

Pyramids/events.out.tfevents.1767769877.MSI.30528.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f332014eefc956dbdfcff08a6973c3f1f2d78e8e40efe4217e80ba6268a081
+size 2806201

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- Pyramids
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Pyramids
+---
+
+  # **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://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  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: Adi070204/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": 256, "buffer_size": 8192, "learning_rate": 0.0001372997890189161, "beta": 0.01351357680858339, "epsilon": 0.17507156497694998, "lambd": 0.938254088365818, "num_epoch": 4, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.03179884085275296, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 1.1017411344137119e-05, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 10000000, "time_horizon": 128, "summary_freq": 20000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "Builds\\UnityEnvironment.exe", "env_args": null, "base_port": 8000, "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": 20.0, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "pyramids_final_best", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,92 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 256
+      buffer_size: 8192
+      learning_rate: 0.0001372997890189161
+      beta: 0.01351357680858339
+      epsilon: 0.17507156497694998
+      lambd: 0.938254088365818
+      num_epoch: 4
+      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
+      curiosity:
+        gamma: 0.99
+        strength: 0.03179884085275296
+        network_settings:
+          normalize: false
+          hidden_units: 256
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 1.1017411344137119e-05
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 1
+    even_checkpoints: false
+    max_steps: 10000000
+    time_horizon: 128
+    summary_freq: 20000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: Builds\UnityEnvironment.exe
+  env_args: null
+  base_port: 8000
+  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: 20.0
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: pyramids_final_best
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,62 @@
+Mono path[0] = 'C:/python/Reinforcement-Learning/ml-agents/Builds/UnityEnvironment_Data/Managed'
+Mono config path = 'C:/python/Reinforcement-Learning/ml-agents/Builds/MonoBleedingEdge/etc'
+Input System module state changed to: Initialized.
+[Physics::Module] Initialized fallback backend.
+[Physics::Module] Id: 0xdecafbad
+Initialize engine version: 6000.0.40f1 (157d81624ddf)
+[Subsystems] Discovering subsystems at path C:/python/Reinforcement-Learning/ml-agents/Builds/UnityEnvironment_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; kGfxThreadingModeNonThreaded
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Loaded All Assemblies, in  0.171 seconds
+- Finished resetting the current domain, in  0.003 seconds
+[Physics::Module] Selected backend.
+[Physics::Module] Name: PhysX
+[Physics::Module] Id: 0xf2b8ea05
+[Physics::Module] SDK Version: 4.1.2
+[Physics::Module] Integration Version: 1.0.0
+[Physics::Module] Threading Mode: Multi-Threaded
+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: '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: '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: '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: 0.464900 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+[Physics::Module] Cleanup current backned.
+[Physics::Module] Id: 0xf2b8ea05
+Input System module state changed to: ShutdownInProgress.
+Input System polling thread exited.
+Input System module state changed to: Shutdown.

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.11422315239906311,
+            "min": 0.10635818541049957,
+            "max": 1.6032832860946655,
+            "count": 500
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 2288.1181640625,
+            "min": 2093.129150390625,
+            "max": 32219.58203125,
+            "count": 500
+        },
+        "Pyramids.Step.mean": {
+            "value": 9999964.0,
+            "min": 19968.0,
+            "max": 9999964.0,
+            "count": 500
+        },
+        "Pyramids.Step.sum": {
+            "value": 9999964.0,
+            "min": 19968.0,
+            "max": 9999964.0,
+            "count": 500
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.8705893158912659,
+            "min": -0.08696519583463669,
+            "max": 0.9940770268440247,
+            "count": 500
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 174.11785888671875,
+            "min": -14.001396179199219,
+            "max": 211.3995361328125,
+            "count": 500
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.10578813403844833,
+            "min": 0.10449855774641037,
+            "max": 4.689557075500488,
+            "count": 500
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.sum": {
+            "value": 21.15762710571289,
+            "min": 20.89971160888672,
+            "max": 753.0303955078125,
+            "count": 500
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.05006951541872695,
+            "min": 0.04121422056505253,
+            "max": 0.058810766625499944,
+            "count": 500
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.1001390308374539,
+            "min": 0.04986661850416567,
+            "max": 0.16531687479982793,
+            "count": 500
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.009665742996730842,
+            "min": 0.0007032624918846362,
+            "max": 0.2743947749001611,
+            "count": 500
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.019331485993461683,
+            "min": 0.0014065249837692724,
+            "max": 0.5487895498003222,
+            "count": 500
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.6590310445924732e-07,
+            "min": 1.6590310445924732e-07,
+            "max": 0.0001371591941373607,
+            "count": 500
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 3.3180620891849464e-07,
+            "min": 3.3180620891849464e-07,
+            "max": 0.00040818917248026574,
+            "count": 500
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10009065642186618,
+            "min": 0.10009065642186618,
+            "max": 0.1749946916944136,
+            "count": 500
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 0.20018131284373236,
+            "min": 0.1749946916944136,
+            "max": 0.5231860660591037,
+            "count": 500
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 2.630691935404572e-05,
+            "min": 2.630691935404572e-05,
+            "max": 0.0134997491459314,
+            "count": 500
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 5.261383870809144e-05,
+            "min": 5.261383870809144e-05,
+            "max": 0.04017582867108255,
+            "count": 500
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.024805564935377333,
+            "min": 0.022652438281511422,
+            "max": 5.399273802340031,
+            "count": 500
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.sum": {
+            "value": 0.04961112987075467,
+            "min": 0.045304876563022844,
+            "max": 5.430380754878646,
+            "count": 500
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.mean": {
+            "value": 0.01703787657424982,
+            "min": 0.012451664861146128,
+            "max": 1.5587653540074826,
+            "count": 500
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.sum": {
+            "value": 0.03407575314849964,
+            "min": 0.024903329722292256,
+            "max": 2.800841969761409,
+            "count": 500
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 190.90196078431373,
+            "min": 168.5137614678899,
+            "max": 999.0,
+            "count": 500
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 19472.0,
+            "min": 14919.0,
+            "max": 31968.0,
+            "count": 500
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.8090980330518647,
+            "min": -1.0000000521540642,
+            "max": 1.8314862271787924,
+            "count": 500
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 184.5279993712902,
+            "min": -31.00000161677599,
+            "max": 213.67299868166447,
+            "count": 500
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.8090980330518647,
+            "min": -1.0000000521540642,
+            "max": 1.8314862271787924,
+            "count": 500
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 184.5279993712902,
+            "min": -31.00000161677599,
+            "max": 213.67299868166447,
+            "count": 500
+        },
+        "Pyramids.Policy.CuriosityReward.mean": {
+            "value": 0.15285808866496617,
+            "min": 0.1338517680683603,
+            "max": 102.52869310975075,
+            "count": 500
+        },
+        "Pyramids.Policy.CuriosityReward.sum": {
+            "value": 15.59152504382655,
+            "min": 13.920583879109472,
+            "max": 1691.8864068984985,
+            "count": 500
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1767769871",
+        "python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr  5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\python\\Reinforcement-Learning\\ml-agents\\.venv\\Scripts\\mlagents-learn optuna_runs\\pyramids_final_best\\final_config.yaml --env Builds\\UnityEnvironment.exe --run-id pyramids_final_best --base-port 8000 --num-envs 1 --force --time-scale 20 --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+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1767788027"
+    },
+    "total": 18156.34620270005,
+    "count": 1,
+    "self": 0.4155688000610098,
+    "children": {
+        "run_training.setup": {
+            "total": 0.15365290001500398,
+            "count": 1,
+            "self": 0.15365290001500398
+        },
+        "TrainerController.start_learning": {
+            "total": 18155.776980999974,
+            "count": 1,
+            "self": 15.2952946331352,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 7.230988299939781,
+                    "count": 1,
+                    "self": 7.230988299939781
+                },
+                "TrainerController.advance": {
+                    "total": 18133.08894036687,
+                    "count": 659181,
+                    "self": 14.994775475468487,
+                    "children": {
+                        "env_step": {
+                            "total": 9079.980078772176,
+                            "count": 659181,
+                            "self": 7798.481798222056,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1271.3684725227067,
+                                    "count": 659181,
+                                    "self": 44.13604481180664,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1227.2324277109,
+                                            "count": 625065,
+                                            "self": 1227.2324277109
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 10.129808027413674,
+                                    "count": 659181,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 18128.24424395815,
+                                            "count": 659181,
+                                            "is_parallel": true,
+                                            "self": 11425.022673878819,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.002118999953381717,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.0002384998369961977,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0018805001163855195,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0018805001163855195
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 6703.219451079378,
+                                                    "count": 659181,
+                                                    "is_parallel": true,
+                                                    "self": 202.9730432110373,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 169.48975574749056,
+                                                            "count": 659181,
+                                                            "is_parallel": true,
+                                                            "self": 169.48975574749056
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 5697.137891348568,
+                                                            "count": 659181,
+                                                            "is_parallel": true,
+                                                            "self": 5697.137891348568
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 633.6187607722823,
+                                                            "count": 659181,
+                                                            "is_parallel": true,
+                                                            "self": 150.71688713051844,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 482.9018736417638,
+                                                                    "count": 5273448,
+                                                                    "is_parallel": true,
+                                                                    "self": 482.9018736417638
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 9038.114086119225,
+                            "count": 659181,
+                            "self": 24.974240463227034,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1428.586373554077,
+                                    "count": 659181,
+                                    "self": 1427.2644285539864,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.3219450000906363,
+                                            "count": 20,
+                                            "self": 1.3219450000906363
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 7584.553472101921,
+                                    "count": 1207,
+                                    "self": 5087.527661683969,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 2497.025810417952,
+                                            "count": 154944,
+                                            "self": 2497.025810417952
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.00003807246685e-07,
+                    "count": 1,
+                    "self": 5.00003807246685e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.16175720002502203,
+                    "count": 1,
+                    "self": 0.1135820000199601,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.048175200005061924,
+                            "count": 1,
+                            "self": 0.048175200005061924
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,29 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 10000092,
+                "file_path": "results\\pyramids_final_best\\Pyramids\\Pyramids-10000092.onnx",
+                "reward": 1.8061499949544668,
+                "creation_time": 1767788027.3648493,
+                "auxillary_file_paths": [
+                    "results\\pyramids_final_best\\Pyramids\\Pyramids-10000092.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 10000092,
+            "file_path": "results\\pyramids_final_best\\Pyramids.onnx",
+            "reward": 1.8061499949544668,
+            "creation_time": 1767788027.3648493,
+            "auxillary_file_paths": [
+                "results\\pyramids_final_best\\Pyramids\\Pyramids-10000092.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cpu"
+    }
+}