First Push`

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9646370a5f78250d7795cd1953697802e93d8994f7ecb4da4635297875fd21
+size 1420238

Pyramids/Pyramids-1499946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62210fb60e29a08669807c1df036a35a8312123ec2ef636a9a79f7821a8cc960
+size 1420238

Pyramids/Pyramids-1499946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4334e6ba8edf73e749b5d57a65ea155f1cc2e90ad73f8e7bda1ac122ed30acaa
+size 8655600

Pyramids/Pyramids-1999914.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9f9d022150272c6d71d097f16a973b743bcc542fc1d7458e2904338a866e6e
+size 1420238

Pyramids/Pyramids-1999914.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e0c4c754f1f2bd3f32a1f0dfa5ebede6bb9d3c433c7b562686e12e529c9fc5
+size 8655600

Pyramids/Pyramids-2499967.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e0fa0a43dcf7ceb1e068818f85a0f6bb182fba7b07e8f0e1919fb84bfb0eaa
+size 1420238

Pyramids/Pyramids-2499967.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b052ae79eae7e2c7f22de53903f5d74bb81225f3bf44e9689095b884472a8d1b
+size 8655600

Pyramids/Pyramids-2830234.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9646370a5f78250d7795cd1953697802e93d8994f7ecb4da4635297875fd21
+size 1420238

Pyramids/Pyramids-2830234.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ad6185f3c4f2e055df189477469aa226b45f263bc7b4fb245b4fc89283ff0f
+size 8655600

Pyramids/Pyramids-999984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84301ee8c42dae0e30b98ce8a3765ccfd4190ed0fdf314b8250d5348edad24a
+size 1420238

Pyramids/Pyramids-999984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0bdaf4282c711fe53f81f0925fcfacfdb4ca432338a71e2680922b0a468663d
+size 8655523

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f574f4b608f4d8464d092d1137bdb6f42935e35a11af3142f859f065b496f10e
+size 8655138

Pyramids/events.out.tfevents.1779775122.colleryu-Moving-Train.37192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd8eb71e7f747e2281c44a9c6d927eaf1771a1641b895e119b5fe72f818d4c8
+size 879554

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: colleryu/ppo-Pyamids-Training
+  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": 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": "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: 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: 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/timers.json

@@ -0,0 +1,356 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.15000031888484955,
+            "min": 0.13954782485961914,
+            "max": 1.3678834438323975,
+            "count": 94
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4454.40966796875,
+            "min": 4181.96923828125,
+            "max": 41496.11328125,
+            "count": 94
+        },
+        "Pyramids.Step.mean": {
+            "value": 2819974.0,
+            "min": 29952.0,
+            "max": 2819974.0,
+            "count": 94
+        },
+        "Pyramids.Step.sum": {
+            "value": 2819974.0,
+            "min": 29952.0,
+            "max": 2819974.0,
+            "count": 94
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.7523895502090454,
+            "min": -0.10804931074380875,
+            "max": 0.8791911005973816,
+            "count": 94
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 218.19297790527344,
+            "min": -26.039884567260742,
+            "max": 271.6700439453125,
+            "count": 94
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.016057733446359634,
+            "min": -0.015474037267267704,
+            "max": 0.3649498224258423,
+            "count": 94
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 4.656742572784424,
+            "min": -4.239886283874512,
+            "max": 86.49311065673828,
+            "count": 94
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06690561315921952,
+            "min": 0.06413568724069987,
+            "max": 0.07396834637190382,
+            "count": 94
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9366785842290731,
+            "min": 0.47693392990445377,
+            "max": 1.0671873185783625,
+            "count": 94
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.012676554747636388,
+            "min": 4.295388629319079e-05,
+            "max": 0.016272034931332908,
+            "count": 94
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.17747176646690943,
+            "min": 0.0005584005218114802,
+            "max": 0.2440805239699936,
+            "count": 94
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.9417307813309527e-05,
+            "min": 1.9417307813309527e-05,
+            "max": 0.00029838354339596195,
+            "count": 94
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.0002718423093863334,
+            "min": 0.0002718423093863334,
+            "max": 0.003969040776986433,
+            "count": 94
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10647240476190477,
+            "min": 0.10647240476190477,
+            "max": 0.19946118095238097,
+            "count": 94
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4906136666666667,
+            "min": 1.3897045333333333,
+            "max": 2.7230135666666664,
+            "count": 94
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.000656593235714286,
+            "min": 0.000656593235714286,
+            "max": 0.009946171977142856,
+            "count": 94
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.009192305300000004,
+            "min": 0.009192305300000004,
+            "max": 0.13230905531,
+            "count": 94
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.006304684095084667,
+            "min": 0.0061477008275687695,
+            "max": 0.4804064929485321,
+            "count": 94
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.08826557546854019,
+            "min": 0.08826557546854019,
+            "max": 3.3628454208374023,
+            "count": 94
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 239.5121951219512,
+            "min": 214.45070422535213,
+            "max": 999.0,
+            "count": 94
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29460.0,
+            "min": 15984.0,
+            "max": 32030.0,
+            "count": 94
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6947360494342008,
+            "min": -1.0000000521540642,
+            "max": 1.7714605462593092,
+            "count": 94
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 206.75779803097248,
+            "min": -32.000001668930054,
+            "max": 251.5473975688219,
+            "count": 94
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6947360494342008,
+            "min": -1.0000000521540642,
+            "max": 1.7714605462593092,
+            "count": 94
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 206.75779803097248,
+            "min": -32.000001668930054,
+            "max": 251.5473975688219,
+            "count": 94
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.015584484200264311,
+            "min": 0.014918969373981563,
+            "max": 10.24926850758493,
+            "count": 94
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.901307072432246,
+            "min": 1.8836493745548069,
+            "max": 163.98829612135887,
+            "count": 94
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 94
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 94
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1779775111",
+        "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul  5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "D:\\anaconda3\\envs\\mlagents\\Scripts\\mlagents-learn ./config/ppo/PyramidsRND.yaml --run-id=Pyramids Training",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.2+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1779779783"
+    },
+    "total": 4671.385533699999,
+    "count": 1,
+    "self": 0.005426200004876591,
+    "children": {
+        "run_training.setup": {
+            "total": 0.07144859999971231,
+            "count": 1,
+            "self": 0.07144859999971231
+        },
+        "TrainerController.start_learning": {
+            "total": 4671.308658899994,
+            "count": 1,
+            "self": 3.4740650018211454,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 11.975379900002736,
+                    "count": 1,
+                    "self": 11.975379900002736
+                },
+                "TrainerController.advance": {
+                    "total": 4655.712553798163,
+                    "count": 182774,
+                    "self": 3.4019469956183457,
+                    "children": {
+                        "env_step": {
+                            "total": 2898.816480400652,
+                            "count": 182774,
+                            "self": 1919.4294330988632,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 977.1693953019567,
+                                    "count": 182774,
+                                    "self": 10.565615301165963,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 966.6037800007907,
+                                            "count": 176937,
+                                            "self": 966.6037800007907
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.2176519998320146,
+                                    "count": 182774,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4655.075940500268,
+                                            "count": 182774,
+                                            "is_parallel": true,
+                                            "self": 2996.2675808005224,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0006253999963519163,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.00016939999477472156,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0004560000015771948,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004560000015771948
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1658.8077342997494,
+                                                    "count": 182774,
+                                                    "is_parallel": true,
+                                                    "self": 45.14729609555798,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 38.16026760155364,
+                                                            "count": 182774,
+                                                            "is_parallel": true,
+                                                            "self": 38.16026760155364
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1434.4124783018633,
+                                                            "count": 182774,
+                                                            "is_parallel": true,
+                                                            "self": 1434.4124783018633
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 141.0876923007745,
+                                                            "count": 182774,
+                                                            "is_parallel": true,
+                                                            "self": 34.32343900355045,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 106.76425329722406,
+                                                                    "count": 1462192,
+                                                                    "is_parallel": true,
+                                                                    "self": 106.76425329722406
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1753.4941264018926,
+                            "count": 182774,
+                            "self": 5.608974703041895,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 341.0756208988096,
+                                    "count": 182774,
+                                    "self": 340.5401445988173,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5354762999922968,
+                                            "count": 5,
+                                            "self": 0.5354762999922968
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1406.809530800041,
+                                    "count": 1300,
+                                    "self": 687.7620055999723,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 719.0475252000688,
+                                            "count": 64541,
+                                            "self": 719.0475252000688
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.00006091594696e-07,
+                    "count": 1,
+                    "self": 8.00006091594696e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.14665940000122646,
+                    "count": 1,
+                    "self": 0.04660670000157552,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.10005269999965094,
+                            "count": 1,
+                            "self": 0.10005269999965094
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 999984,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-999984.onnx",
+                "reward": 1.0585333208243053,
+                "creation_time": 1779776777.7400672,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-999984.pt"
+                ]
+            },
+            {
+                "steps": 1499946,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-1499946.onnx",
+                "reward": 1.7129999697208405,
+                "creation_time": 1779777587.9230256,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-1499946.pt"
+                ]
+            },
+            {
+                "steps": 1999914,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-1999914.onnx",
+                "reward": null,
+                "creation_time": 1779778411.4033597,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-1999914.pt"
+                ]
+            },
+            {
+                "steps": 2499967,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-2499967.onnx",
+                "reward": 1.4298571252397128,
+                "creation_time": 1779779238.4300816,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-2499967.pt"
+                ]
+            },
+            {
+                "steps": 2830234,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-2830234.onnx",
+                "reward": null,
+                "creation_time": 1779779783.0345035,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-2830234.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 2830234,
+            "file_path": "results\\Pyramids Training\\Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1779779783.0345035,
+            "auxillary_file_paths": [
+                "results\\Pyramids Training\\Pyramids\\Pyramids-2830234.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.2.2+cu121"
+    }
+}