5m steps

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+run_logs/Player-0.log filter=lfs diff=lfs merge=lfs -text

Heli.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efafe4fde91a35216e645d3efff889a6140087bb3d17806008345e6c9fc08710
+size 2187053

Heli/Heli-1249792.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5560542367f4d30034fceb58188298bf94bf8b5440f126ed815a8432af21bbd8
+size 2187053

Heli/Heli-1249792.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0490f426509bc1c31a72d9753a52fe22d304d482501d9b247fde4ac0f0a4ab8
+size 14922498

Heli/Heli-1398016.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efafe4fde91a35216e645d3efff889a6140087bb3d17806008345e6c9fc08710
+size 2187053

Heli/Heli-1398016.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70f328425d5fd9f32505dec64cc177dde25cd54afd7b5dd1681265b8962a318
+size 14922498

Heli/Heli-249993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d60ad210e3e1a409ff986e4b3ad41e825878043457abf2ac2e8b7d42d84f9b
+size 2187053

Heli/Heli-249993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ae0b59909825197bfb9f1d01a419fce7a08c627bdaa0d7ae1bde2f49bcc439
+size 14922498

Heli/Heli-499984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be30046a600ab887228ccdbb9bc19e7fc985349762f1f2442d0bcc575ec49f4e
+size 2187053

Heli/Heli-499984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f93f9e40157a743d7c612ac8e540b4f1ffeb7b5c53a1a5e2624622b8c154b99d
+size 14922498

Heli/Heli-749884.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc232165b2b06c191e692988ee9fd8ba5fcf1e9a5bb0b8219e845cf24d90bd3
+size 2187053

Heli/Heli-749884.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54e601f66908a3426241ca1f63ccde6f6672b52da67c15d9c3f0006cd507828
+size 14922498

Heli/Heli-999718.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20bb392c627e57bcd0ce299d89676b47149d6249678aa44aa5415985d6068284
+size 2187053

Heli/Heli-999718.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7795e9702140a59ca4c386bdef0af0582a7862eaf02ab60527f1f49b5e7ddf2d
+size 14922498

Heli/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70f328425d5fd9f32505dec64cc177dde25cd54afd7b5dd1681265b8962a318
+size 14922498

Heli/events.out.tfevents.1691441418.28cc7e6db715.1368.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23d97b12129a198b7a439b5ea23cb4646623ceb9ab99124021c111cfebd6b20a
+size 529124

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- Heli
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Heli
+---
+
+  # **ppo** Agent playing **Heli**
+  This is a trained model of a **ppo** agent playing **Heli**
+  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: AtilliO/Chopper03_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": {"Heli": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 10240, "learning_rate": 0.0002, "beta": 0.001, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 250000, "network_settings": {"normalize": true, "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": 15, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 512, "summary_freq": 5000, "threaded": true, "self_play": null, "behavioral_cloning": null}, "LoaderG": {"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": 2000000, "time_horizon": 512, "summary_freq": 5000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/ChopperLnx03/ChopperLnx03", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Chopper03_00", "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 +1,147 @@
+default_settings: null
+behaviors:
+  Heli:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 256
+      buffer_size: 10240
+      learning_rate: 0.0002
+      beta: 0.001
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 250000
+    network_settings:
+      normalize: true
+      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: 15
+    even_checkpoints: false
+    max_steps: 5000000
+    time_horizon: 512
+    summary_freq: 5000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+  LoaderG:
+    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: 2000000
+    time_horizon: 512
+    summary_freq: 5000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/ChopperLnx03/ChopperLnx03
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: Chopper03_00
+  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 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c645e09fea9fb76611de85df0fa65038b5205a10bb0c0131652055ebedfc37
+size 17480447

run_logs/timers.json

@@ -0,0 +1,180 @@
+{
+    "name": "root",
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1691441414",
+        "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Beach.yaml --env=./training-envs-executables/linux/ChopperLnx03/ChopperLnx03 --run-id=Chopper03_00 --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1691449384"
+    },
+    "total": 7969.14715323,
+    "count": 1,
+    "self": 0.19158281999989413,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05618040300004168,
+            "count": 1,
+            "self": 0.05618040300004168
+        },
+        "TrainerController.start_learning": {
+            "total": 7968.899390007,
+            "count": 1,
+            "self": 20.382382175747807,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.289941060999979,
+                    "count": 1,
+                    "self": 3.289941060999979
+                },
+                "TrainerController.advance": {
+                    "total": 7944.670017396253,
+                    "count": 351347,
+                    "self": 9.456127876464961,
+                    "children": {
+                        "env_step": {
+                            "total": 7935.213889519788,
+                            "count": 351347,
+                            "self": 5258.841016150836,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2666.7732618971004,
+                                    "count": 351347,
+                                    "self": 55.13522642679436,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2611.638035470306,
+                                            "count": 349687,
+                                            "self": 2611.638035470306
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 9.599611471851006,
+                                    "count": 351346,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 7928.148748510179,
+                                            "count": 351346,
+                                            "is_parallel": true,
+                                            "self": 4338.461399475137,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.006323793999968075,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.004990665999855537,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0013331280001125378,
+                                                                    "count": 6,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0013331280001125378
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04867976399998497,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00044687900003737013,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003752380000037192,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003752380000037192
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.04638975899996467,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.04638975899996467
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0014678879999792116,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004198669999482263,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0010480210000309853,
+                                                                            "count": 6,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0010480210000309853
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3589.6873490350417,
+                                                    "count": 351345,
+                                                    "is_parallel": true,
+                                                    "self": 152.38421451770046,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 94.76092162134836,
+                                                            "count": 351345,
+                                                            "is_parallel": true,
+                                                            "self": 94.76092162134836
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2819.983938868857,
+                                                            "count": 351345,
+                                                            "is_parallel": true,
+                                                            "self": 2819.983938868857
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 522.5582740271361,
+                                                            "count": 351345,
+                                                            "is_parallel": true,
+                                                            "self": 149.29340560353978,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 373.26486842359634,
+                                                                    "count": 2108070,
+                                                                    "is_parallel": true,
+                                                                    "self": 373.26486842359634
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.5570493739996891,
+                    "count": 1,
+                    "self": 0.0034515099996497156,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.5535978640000394,
+                            "count": 1,
+                            "self": 0.5535978640000394
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,74 @@
+{
+    "Heli": {
+        "checkpoints": [
+            {
+                "steps": 249993,
+                "file_path": "results/Chopper03_00/Heli/Heli-249993.onnx",
+                "reward": 11.883715203830175,
+                "creation_time": 1691442859.65759,
+                "auxillary_file_paths": [
+                    "results/Chopper03_00/Heli/Heli-249993.pt"
+                ]
+            },
+            {
+                "steps": 499984,
+                "file_path": "results/Chopper03_00/Heli/Heli-499984.onnx",
+                "reward": 14.810667872428894,
+                "creation_time": 1691444310.6054258,
+                "auxillary_file_paths": [
+                    "results/Chopper03_00/Heli/Heli-499984.pt"
+                ]
+            },
+            {
+                "steps": 749884,
+                "file_path": "results/Chopper03_00/Heli/Heli-749884.onnx",
+                "reward": 15.142001390457153,
+                "creation_time": 1691445755.4532797,
+                "auxillary_file_paths": [
+                    "results/Chopper03_00/Heli/Heli-749884.pt"
+                ]
+            },
+            {
+                "steps": 999718,
+                "file_path": "results/Chopper03_00/Heli/Heli-999718.onnx",
+                "reward": 10.120750904083252,
+                "creation_time": 1691447193.6663072,
+                "auxillary_file_paths": [
+                    "results/Chopper03_00/Heli/Heli-999718.pt"
+                ]
+            },
+            {
+                "steps": 1249792,
+                "file_path": "results/Chopper03_00/Heli/Heli-1249792.onnx",
+                "reward": null,
+                "creation_time": 1691448604.015588,
+                "auxillary_file_paths": [
+                    "results/Chopper03_00/Heli/Heli-1249792.pt"
+                ]
+            },
+            {
+                "steps": 1398016,
+                "file_path": "results/Chopper03_00/Heli/Heli-1398016.onnx",
+                "reward": 11.389445361163881,
+                "creation_time": 1691449383.8313968,
+                "auxillary_file_paths": [
+                    "results/Chopper03_00/Heli/Heli-1398016.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1398016,
+            "file_path": "results/Chopper03_00/Heli.onnx",
+            "reward": 11.389445361163881,
+            "creation_time": 1691449383.8313968,
+            "auxillary_file_paths": [
+                "results/Chopper03_00/Heli/Heli-1398016.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}