First push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ea443e4f8e6d278d63376fcf4beb0b1cb86452abc22c3296356fb411babdad
+size 1420238

Pyramids/Pyramids-10000044.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ea443e4f8e6d278d63376fcf4beb0b1cb86452abc22c3296356fb411babdad
+size 1420238

Pyramids/Pyramids-10000044.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f527d951b9034c61cfa6bb15a8cbe9e49ec20299e40eb24d5f6ab26e032ff0
+size 10002123

Pyramids/Pyramids-8499966.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:346e4933461777237cc962fb92bc6f9db59f58db052fdf6059e68c50d19ddcb7
+size 1420238

Pyramids/Pyramids-8499966.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bf416543947247028829e056fae96f4a782a133561a1546eff65b21ed09e9a
+size 10002044

Pyramids/Pyramids-8999901.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fbef9d0164eeba1bdc26d115848d938dbd1a2e81c50d57916d4401612d1e862
+size 1420238

Pyramids/Pyramids-8999901.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4376c9ceed196000866144b3316bc6138946eb431490b694fc4657d3e42be6
+size 10002044

Pyramids/Pyramids-9499969.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1048e0768cb55a793aa76d5db55cb1687970c73013b3b25a80b6fb2c530f8e1e
+size 1420238

Pyramids/Pyramids-9499969.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f350dfe74520b632bd4bff6fcb582a2e7ec759349d15c0c91dfa603a3e0d121
+size 10002044

Pyramids/Pyramids-9999916.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ea443e4f8e6d278d63376fcf4beb0b1cb86452abc22c3296356fb411babdad
+size 1420238

Pyramids/Pyramids-9999916.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a7222fecf2fd8c43419d6d8e6e3183305cb87688b66b51e2e9d85b80ca2b08
+size 10002044

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e37f046bdd75fce87240b1f503bc1845eb49d9b43ee533077396fd2a7b3e53
+size 10001506

Pyramids/events.out.tfevents.1711138902.MacBook-Pro-de-Paul.local.15473.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a218097a52a5d93905ed71c438eaf18e4789e1860f363b3b9c8eb1fe2836ba6
+size 2723399

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: PaulTbbr/ppo-pyramids-00
+  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}}, "curiosity": {"gamma": 0.99, "strength": 0.02, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 10000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": null, "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": false, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids00", "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
+      curiosity:
+        gamma: 0.99
+        strength: 0.02
+        network_settings:
+          normalize: false
+          hidden_units: 256
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0003
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 10000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: null
+  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: false
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids00
+  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/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.09659828245639801,
+            "min": 0.08577015995979309,
+            "max": 1.4727826118469238,
+            "count": 333
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 2897.948486328125,
+            "min": 2615.646728515625,
+            "max": 44678.33203125,
+            "count": 333
+        },
+        "Pyramids.Step.mean": {
+            "value": 9989950.0,
+            "min": 29952.0,
+            "max": 9989950.0,
+            "count": 333
+        },
+        "Pyramids.Step.sum": {
+            "value": 9989950.0,
+            "min": 29952.0,
+            "max": 9989950.0,
+            "count": 333
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.9547367691993713,
+            "min": -0.10988577455282211,
+            "max": 1.004745602607727,
+            "count": 333
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 299.787353515625,
+            "min": -26.482471466064453,
+            "max": 323.528076171875,
+            "count": 333
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.030147476121783257,
+            "min": 0.025316940620541573,
+            "max": 0.41487738490104675,
+            "count": 333
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.sum": {
+            "value": 9.466307640075684,
+            "min": 7.822934627532959,
+            "max": 99.82791137695312,
+            "count": 333
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.0673175727230652,
+            "min": 0.06232600730644273,
+            "max": 0.07484725077032427,
+            "count": 333
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9424460181229127,
+            "min": 0.47229922364479937,
+            "max": 1.1045833782774541,
+            "count": 333
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.013726562569943436,
+            "min": 6.54922021441563e-05,
+            "max": 0.017306548792735806,
+            "count": 333
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.1921718759792081,
+            "min": 0.0009168908300181881,
+            "max": 0.24229168309830126,
+            "count": 333
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.38710468082143e-07,
+            "min": 7.38710468082143e-07,
+            "max": 0.0002995150630187886,
+            "count": 333
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 1.0341946553150002e-05,
+            "min": 1.0341946553150002e-05,
+            "max": 0.0040343232352256396,
+            "count": 333
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10024620357142858,
+            "min": 0.10024620357142858,
+            "max": 0.1998383542857143,
+            "count": 333
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4034468500000001,
+            "min": 1.38850944,
+            "max": 2.8447743599999997,
+            "count": 333
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 3.45957367857143e-05,
+            "min": 3.45957367857143e-05,
+            "max": 0.009983851593142858,
+            "count": 333
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0004843403150000002,
+            "min": 0.0004843403150000002,
+            "max": 0.134492958564,
+            "count": 333
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.010238115377779605,
+            "min": 0.008714325094409841,
+            "max": 0.4099465698968735,
+            "count": 333
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.sum": {
+            "value": 0.14333361528891447,
+            "min": 0.12200055132173777,
+            "max": 2.8696259892781146,
+            "count": 333
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.mean": {
+            "value": 0.0057052407149577825,
+            "min": 0.002950076695603659,
+            "max": 0.7842482853396406,
+            "count": 333
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.sum": {
+            "value": 0.07987337000940896,
+            "min": 0.044251150434054885,
+            "max": 5.4897379973774845,
+            "count": 333
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 186.1556886227545,
+            "min": 171.22085889570553,
+            "max": 999.0,
+            "count": 333
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 31088.0,
+            "min": 15984.0,
+            "max": 34211.0,
+            "count": 333
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7891301097550305,
+            "min": -1.0000000521540642,
+            "max": 1.8287791264203428,
+            "count": 333
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 296.9955982193351,
+            "min": -32.000001668930054,
+            "max": 314.61059732735157,
+            "count": 333
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7891301097550305,
+            "min": -1.0000000521540642,
+            "max": 1.8287791264203428,
+            "count": 333
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 296.9955982193351,
+            "min": -32.000001668930054,
+            "max": 314.61059732735157,
+            "count": 333
+        },
+        "Pyramids.Policy.CuriosityReward.mean": {
+            "value": 0.03991356181367917,
+            "min": 0.03410876181021051,
+            "max": 7.369642803445458,
+            "count": 333
+        },
+        "Pyramids.Policy.CuriosityReward.sum": {
+            "value": 6.625651261070743,
+            "min": 5.184531795151997,
+            "max": 167.39837768673897,
+            "count": 333
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 333
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 333
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1711138897",
+        "python_version": "3.10.1 (main, Mar 20 2024, 23:11:47) [Clang 15.0.0 (clang-1500.3.9.4)]",
+        "command_line_arguments": "/Users/paul/.pyenv/versions/3.10.1/envs/venv_unit5_hf/bin/mlagents-learn config/ppo/Pyramids.yaml --run-id Pyramids00",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1711155413"
+    },
+    "total": 16515.837095,
+    "count": 1,
+    "self": 0.0032615419950161595,
+    "children": {
+        "run_training.setup": {
+            "total": 0.014169707999826642,
+            "count": 1,
+            "self": 0.014169707999826642
+        },
+        "TrainerController.start_learning": {
+            "total": 16515.819663750004,
+            "count": 1,
+            "self": 5.050972458069737,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.200303416000679,
+                    "count": 1,
+                    "self": 5.200303416000679
+                },
+                "TrainerController.advance": {
+                    "total": 16505.53490170994,
+                    "count": 655734,
+                    "self": 5.053516233303526,
+                    "children": {
+                        "env_step": {
+                            "total": 13992.83843329976,
+                            "count": 655734,
+                            "self": 13668.814883681367,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 320.4675482351122,
+                                    "count": 655734,
+                                    "self": 11.787854892958421,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 308.67969334215377,
+                                            "count": 625052,
+                                            "self": 308.67969334215377
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 3.5560013832800905,
+                                    "count": 655734,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 16503.084301704188,
+                                            "count": 655734,
+                                            "is_parallel": true,
+                                            "self": 3187.134702260697,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0005815830008941703,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.00012183199942228384,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0004597510014718864,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004597510014718864
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 13315.94901786049,
+                                                    "count": 655734,
+                                                    "is_parallel": true,
+                                                    "self": 39.6326328279647,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 185.1218753106259,
+                                                            "count": 655734,
+                                                            "is_parallel": true,
+                                                            "self": 185.1218753106259
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 12774.521226542933,
+                                                            "count": 655734,
+                                                            "is_parallel": true,
+                                                            "self": 12774.521226542933
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 316.6732831789668,
+                                                            "count": 655734,
+                                                            "is_parallel": true,
+                                                            "self": 55.268841222059564,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 261.40444195690725,
+                                                                    "count": 5245872,
+                                                                    "is_parallel": true,
+                                                                    "self": 261.40444195690725
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2507.642952176877,
+                            "count": 655734,
+                            "self": 9.581380121315306,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 436.2491943975365,
+                                    "count": 655734,
+                                    "self": 435.53307568854143,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.7161187089950545,
+                                            "count": 20,
+                                            "self": 0.7161187089950545
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2061.812377658025,
+                                    "count": 4649,
+                                    "self": 1470.146524662432,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 591.665852995593,
+                                            "count": 227991,
+                                            "self": 591.665852995593
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 3.749955794773996e-07,
+                    "count": 1,
+                    "self": 3.749955794773996e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.03348579099838389,
+                    "count": 1,
+                    "self": 0.0004614159988705069,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.033024374999513384,
+                            "count": 1,
+                            "self": 0.033024374999513384
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 8499966,
+                "file_path": "results/Pyramids00/Pyramids/Pyramids-8499966.onnx",
+                "reward": null,
+                "creation_time": 1711152905.320728,
+                "auxillary_file_paths": [
+                    "results/Pyramids00/Pyramids/Pyramids-8499966.pt"
+                ]
+            },
+            {
+                "steps": 8999901,
+                "file_path": "results/Pyramids00/Pyramids/Pyramids-8999901.onnx",
+                "reward": 1.8924999833106995,
+                "creation_time": 1711153744.818826,
+                "auxillary_file_paths": [
+                    "results/Pyramids00/Pyramids/Pyramids-8999901.pt"
+                ]
+            },
+            {
+                "steps": 9499969,
+                "file_path": "results/Pyramids00/Pyramids/Pyramids-9499969.onnx",
+                "reward": 1.5809999711811542,
+                "creation_time": 1711154574.8163252,
+                "auxillary_file_paths": [
+                    "results/Pyramids00/Pyramids/Pyramids-9499969.pt"
+                ]
+            },
+            {
+                "steps": 9999916,
+                "file_path": "results/Pyramids00/Pyramids/Pyramids-9999916.onnx",
+                "reward": 1.8183333228031795,
+                "creation_time": 1711155413.550189,
+                "auxillary_file_paths": [
+                    "results/Pyramids00/Pyramids/Pyramids-9999916.pt"
+                ]
+            },
+            {
+                "steps": 10000044,
+                "file_path": "results/Pyramids00/Pyramids/Pyramids-10000044.onnx",
+                "reward": 1.8183333228031795,
+                "creation_time": 1711155413.587848,
+                "auxillary_file_paths": [
+                    "results/Pyramids00/Pyramids/Pyramids-10000044.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 10000044,
+            "file_path": "results/Pyramids00/Pyramids.onnx",
+            "reward": 1.8183333228031795,
+            "creation_time": 1711155413.587848,
+            "auxillary_file_paths": [
+                "results/Pyramids00/Pyramids/Pyramids-10000044.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1"
+    }
+}