First training of ML-Agents Pyramids

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99291eb6815c4bc4d05acbe2f47692aee2fa6b639129cadd30d0ecdf3c364d86
+size 1420238

Pyramids/Pyramids-1499960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7257b97ec601e2d85ee2b022fbc2a78e17360ea257a2c8850540e57d76ff8fa
+size 1420238

Pyramids/Pyramids-1499960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6020bf5b66215f7e8c41b351ca1614101c5e1eff3ea50473b3ea7e6fd6032b39
+size 8656252

Pyramids/Pyramids-1999993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58338abaec209b7845a2a70994a772515337d4aaa7f894538aed5771928f4155
+size 1420238

Pyramids/Pyramids-1999993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709a21fbc55258706115e5e108d0d8b7e0242b6ef824de22d55426c51f2d5b99
+size 8656252

Pyramids/Pyramids-2499893.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbdd931f9937d1c15651d5d4247f6f01898f07aa63adeb7c28286fa685ca66b
+size 1420238

Pyramids/Pyramids-2499893.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f7858df59282a9486738992bf7d6edd5fbef8f94306114328b2b569337c54d
+size 8656252

Pyramids/Pyramids-2999961.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99291eb6815c4bc4d05acbe2f47692aee2fa6b639129cadd30d0ecdf3c364d86
+size 1420238

Pyramids/Pyramids-2999961.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f9f44718309f7799103cf8e5462a341aac1a89356ac27257733eb7348c0af2
+size 8656252

Pyramids/Pyramids-3000089.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99291eb6815c4bc4d05acbe2f47692aee2fa6b639129cadd30d0ecdf3c364d86
+size 1420238

Pyramids/Pyramids-3000089.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f446483435fd7e0c1a4c6c39566d05f90c3e4f8acd3d9f73872b644b473b6589
+size 8656252

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6488ec5dc1c88bc3352c384288f1d41436a8f34a4f34027f077106eb51eda21
+size 8655778

Pyramids/events.out.tfevents.1731688235.Christian.10232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34f5bc9e241a0e712fd9c54669e9d0f384e86017be34e13e00a8f72272d9a4b
+size 848952

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: ch-bz/ppo-Pyramids-v1
+  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, "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": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./build/UnityEnvironment", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,92 @@
+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: 3000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./build/UnityEnvironment
+  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

run_logs/Player-0.log

@@ -0,0 +1,58 @@
+Mono path[0] = 'C:/Users/songo/Documents/Python/DeepRLCourse/Unit5/ml-agents/build/UnityEnvironment_Data/Managed'
+Mono config path = 'C:/Users/songo/Documents/Python/DeepRLCourse/Unit5/ml-agents/build/MonoBleedingEdge/etc'
+[Physics::Module] Initialized fallback backend.
+[Physics::Module] Id: 0xdecafbad
+Initialize engine version: 6000.0.26f1 (ccb7c73d2c02)
+[Subsystems] Discovering subsystems at path C:/Users/songo/Documents/Python/DeepRLCourse/Unit5/ml-agents/build/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  0.119 seconds
+- Finished resetting the current domain, in  0.002 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: 0.764500 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

run_logs/timers.json

@@ -0,0 +1,356 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.14624297618865967,
+            "min": 0.14624297618865967,
+            "max": 1.4647560119628906,
+            "count": 100
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4429.4072265625,
+            "min": 4429.4072265625,
+            "max": 44434.83984375,
+            "count": 100
+        },
+        "Pyramids.Step.mean": {
+            "value": 2999961.0,
+            "min": 29952.0,
+            "max": 2999961.0,
+            "count": 100
+        },
+        "Pyramids.Step.sum": {
+            "value": 2999961.0,
+            "min": 29952.0,
+            "max": 2999961.0,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.8048204183578491,
+            "min": -0.09897731989622116,
+            "max": 0.8590055704116821,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 238.22683715820312,
+            "min": -23.853534698486328,
+            "max": 261.1376953125,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.003933842293918133,
+            "min": -0.027270613238215446,
+            "max": 0.41345709562301636,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -1.1644172668457031,
+            "min": -8.099371910095215,
+            "max": 97.98933410644531,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.07051334704668816,
+            "min": 0.06429423743355771,
+            "max": 0.07545404697173377,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9871868586536342,
+            "min": 0.48659723690472106,
+            "max": 1.1318107045760066,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.013090788689580569,
+            "min": 0.00012420112438344576,
+            "max": 0.01626293453672487,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.18327104165412797,
+            "min": 0.0013662123682179033,
+            "max": 0.24394401805087304,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.5376566303380957e-06,
+            "min": 1.5376566303380957e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.152719282473334e-05,
+            "min": 2.152719282473334e-05,
+            "max": 0.0037177996607335,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10051251904761904,
+            "min": 0.10051251904761904,
+            "max": 0.19946118095238097,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4071752666666666,
+            "min": 1.3897045333333333,
+            "max": 2.737489833333334,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 6.120065285714288e-05,
+            "min": 6.120065285714288e-05,
+            "max": 0.009946171977142856,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0008568091400000004,
+            "min": 0.0008568091400000004,
+            "max": 0.12394272335000002,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.004076735116541386,
+            "min": 0.004063901957124472,
+            "max": 0.3282770812511444,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.05707429349422455,
+            "min": 0.05689462646842003,
+            "max": 2.2979395389556885,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 220.21875,
+            "min": 217.84285714285716,
+            "max": 999.0,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28188.0,
+            "min": 15984.0,
+            "max": 33669.0,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.779781237593852,
+            "min": -1.0000000521540642,
+            "max": 1.779781237593852,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 227.81199841201305,
+            "min": -32.000001668930054,
+            "max": 245.50119867920876,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.779781237593852,
+            "min": -1.0000000521540642,
+            "max": 1.779781237593852,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 227.81199841201305,
+            "min": -32.000001668930054,
+            "max": 245.50119867920876,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.00933070190561125,
+            "min": 0.009300382798619467,
+            "max": 6.441338911652565,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.19432984391824,
+            "min": 1.19432984391824,
+            "max": 103.06142258644104,
+            "count": 100
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1731688232",
+        "python_version": "3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\songo\\Documents\\Python\\DeepRLCourse\\Scripts\\mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./build/UnityEnvironment --run-id=Pyramids Training --no-graphics",
+        "mlagents_version": "1.1.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1731692835"
+    },
+    "total": 4603.306294100001,
+    "count": 1,
+    "self": 0.25035030000435654,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1570873999989999,
+            "count": 1,
+            "self": 0.1570873999989999
+        },
+        "TrainerController.start_learning": {
+            "total": 4602.898856399997,
+            "count": 1,
+            "self": 3.2654007006676693,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.993731700000353,
+                    "count": 1,
+                    "self": 4.993731700000353
+                },
+                "TrainerController.advance": {
+                    "total": 4594.527222799328,
+                    "count": 194290,
+                    "self": 2.8569732006544655,
+                    "children": {
+                        "env_step": {
+                            "total": 2418.813839399236,
+                            "count": 194290,
+                            "self": 1775.8495642986854,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 640.8690928998167,
+                                    "count": 194290,
+                                    "self": 9.036510999510938,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 631.8325819003057,
+                                            "count": 187570,
+                                            "self": 631.8325819003057
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.0951822007336887,
+                                    "count": 194290,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4595.95136709964,
+                                            "count": 194290,
+                                            "is_parallel": true,
+                                            "self": 3041.8285563000045,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0008488000003126217,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.0001990000000660075,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0006498000002466142,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006498000002466142
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1554.1219619996355,
+                                                    "count": 194290,
+                                                    "is_parallel": true,
+                                                    "self": 51.483499799524,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 34.75150880024921,
+                                                            "count": 194290,
+                                                            "is_parallel": true,
+                                                            "self": 34.75150880024921
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1333.029609400386,
+                                                            "count": 194290,
+                                                            "is_parallel": true,
+                                                            "self": 1333.029609400386
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 134.85734399947614,
+                                                            "count": 194290,
+                                                            "is_parallel": true,
+                                                            "self": 26.87234490111223,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 107.98499909836391,
+                                                                    "count": 1554320,
+                                                                    "is_parallel": true,
+                                                                    "self": 107.98499909836391
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2172.856410199438,
+                            "count": 194290,
+                            "self": 6.307676598404214,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 351.15190310101025,
+                                    "count": 194290,
+                                    "self": 350.5796433010091,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5722598000011203,
+                                            "count": 6,
+                                            "self": 0.5722598000011203
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1815.3968305000235,
+                                    "count": 1376,
+                                    "self": 812.0426447996033,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 1003.3541857004202,
+                                            "count": 68484,
+                                            "self": 1003.3541857004202
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.000009307172149e-07,
+                    "count": 1,
+                    "self": 6.000009307172149e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.11250060000020312,
+                    "count": 1,
+                    "self": 0.03100059999997029,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08150000000023283,
+                            "count": 1,
+                            "self": 0.08150000000023283
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 1499960,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-1499960.onnx",
+                "reward": 1.7964999992400408,
+                "creation_time": 1731690513.8980315,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-1499960.pt"
+                ]
+            },
+            {
+                "steps": 1999993,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-1999993.onnx",
+                "reward": 1.7779999990016222,
+                "creation_time": 1731691279.575953,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-1999993.pt"
+                ]
+            },
+            {
+                "steps": 2499893,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-2499893.onnx",
+                "reward": null,
+                "creation_time": 1731692048.6829982,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-2499893.pt"
+                ]
+            },
+            {
+                "steps": 2999961,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-2999961.onnx",
+                "reward": 1.8303999781608582,
+                "creation_time": 1731692835.3179293,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-2999961.pt"
+                ]
+            },
+            {
+                "steps": 3000089,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-3000089.onnx",
+                "reward": 1.8303999781608582,
+                "creation_time": 1731692835.4158523,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-3000089.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 3000089,
+            "file_path": "results\\Pyramids Training\\Pyramids.onnx",
+            "reward": 1.8303999781608582,
+            "creation_time": 1731692835.4158523,
+            "auxillary_file_paths": [
+                "results\\Pyramids Training\\Pyramids\\Pyramids-3000089.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0",
+        "torch_version": "2.5.1+cu124"
+    }
+}