default parameters training

.DS_Store

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1193e8cb5bc5289f07d81d84e3fcc21b031ab5b793b625cc36298e5f3b6396ba
+size 6148

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard 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
+.DS_Store filter=lfs diff=lfs merge=lfs -text

Crawler.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1b5412d042c641eaae50cf1cf88541adaa04682c42d1446f3857e15ad4ef56
+size 2472170

Crawler/Crawler-10000355.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1b5412d042c641eaae50cf1cf88541adaa04682c42d1446f3857e15ad4ef56
+size 2472170

Crawler/Crawler-10000355.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf70abaf4b26d61bbad46bc08f388460bd7c200d908cde34f77ba5915f5ed3c
+size 14720683

Crawler/Crawler-8499475.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d464ba4f05930b192cf195cbd09099cc286116c7e795fa8f83b68d30c54a6e3c
+size 2472170

Crawler/Crawler-8499475.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9037f01fc1e4c0fb85a1b741ee69f0a8b51523b1eed57a3ab426a3f3e5d3b8f4
+size 14720683

Crawler/Crawler-8999283.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb97ec2968cbb306d21d5963a7cfa4d854ddb444ab33cd704938a1ccd397d6d
+size 2472170

Crawler/Crawler-8999283.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a437f4ce661bf1c8059575319f58fd881c9e786caf09d85317aad843ab084973
+size 14720683

Crawler/Crawler-9499691.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2384d4d0dc77be0aa1390d2df8c250f37b67c8af851823b2139f7d872d6347b9
+size 2472170

Crawler/Crawler-9499691.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19f4d6824b9eb20abed96d1b3e4172ac6fce6cc1be738cd33f2972aacb3f98d
+size 14720683

Crawler/Crawler-9999355.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3b7eed349ea699722d3bfa554d97a01f496cddbe964d2dc6bbb274cbf55af1
+size 2472170

Crawler/Crawler-9999355.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a75bb497a00e93bfa84a92f6bd2a0615513e9c167f8a2c333f76ff6e733a207
+size 14720683

Crawler/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf70abaf4b26d61bbad46bc08f388460bd7c200d908cde34f77ba5915f5ed3c
+size 14720683

Crawler/events.out.tfevents.1657940151.Joydeeps-MacBook-Pro.local.56438.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c9098fc4948a8a0a4890cb1f9081ad12aae6bb6b0e3fe591095c98c43a62be
+size 1476975

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-Crawler
+      library_name: ml-agents
+---
+    
+  # **ppo** Agent playing **Crawler**
+  This is a trained model of a **ppo** agent playing **Crawler** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+  
+  ## Usage (with ML-Agents)
+  The Documentation: https://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-Crawler
+  2. Step 1: Write your model_id: infinitejoy/MLAgents-Crawler
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Crawler": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 10000000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/macos/crawler/crawler", "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": "firstCrawlerRun2", "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 +1,75 @@
+default_settings: null
+behaviors:
+  Crawler:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        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
+    init_path: null
+    keep_checkpoints: 5
+    checkpoint_interval: 500000
+    max_steps: 10000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./trained-envs-executables/macos/crawler/crawler
+  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: firstCrawlerRun2
+  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 sha256:5b594c9648038f056b36d4d5e058c67fc024d18369abe013f3f7718bab0ebe14
+size 96835713

run_logs/timers.json

@@ -0,0 +1,327 @@
+{
+    "name": "root",
+    "gauges": {
+        "Crawler.Policy.Entropy.mean": {
+            "value": 1.2496061325073242,
+            "min": 1.2496057748794556,
+            "max": 1.4187427759170532,
+            "count": 333
+        },
+        "Crawler.Policy.Entropy.sum": {
+            "value": 37488.18359375,
+            "min": 35124.23828125,
+            "max": 44984.64453125,
+            "count": 333
+        },
+        "Crawler.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 6.280029119145838,
+            "max": 999.0,
+            "count": 333
+        },
+        "Crawler.Environment.EpisodeLength.sum": {
+            "value": 29970.0,
+            "min": 25880.0,
+            "max": 30867.0,
+            "count": 333
+        },
+        "Crawler.Step.mean": {
+            "value": 9989355.0,
+            "min": 29994.0,
+            "max": 9989355.0,
+            "count": 333
+        },
+        "Crawler.Step.sum": {
+            "value": 9989355.0,
+            "min": 29994.0,
+            "max": 9989355.0,
+            "count": 333
+        },
+        "Crawler.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 543.0842895507812,
+            "min": -0.9754056930541992,
+            "max": 644.7567138671875,
+            "count": 333
+        },
+        "Crawler.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 16292.529296875,
+            "min": -3863.58203125,
+            "max": 19817.427734375,
+            "count": 333
+        },
+        "Crawler.Environment.CumulativeReward.mean": {
+            "value": 2699.875163777669,
+            "min": -0.9966317880211525,
+            "max": 3193.4734334309896,
+            "count": 333
+        },
+        "Crawler.Environment.CumulativeReward.sum": {
+            "value": 80996.25491333008,
+            "min": -4106.122966647148,
+            "max": 95804.20300292969,
+            "count": 333
+        },
+        "Crawler.Policy.ExtrinsicReward.mean": {
+            "value": 2699.875163777669,
+            "min": -0.9966317880211525,
+            "max": 3193.4734334309896,
+            "count": 333
+        },
+        "Crawler.Policy.ExtrinsicReward.sum": {
+            "value": 80996.25491333008,
+            "min": -4106.122966647148,
+            "max": 95804.20300292969,
+            "count": 333
+        },
+        "Crawler.Losses.PolicyLoss.mean": {
+            "value": 0.01621496935331379,
+            "min": 0.011323035595705733,
+            "max": 0.02383574066722455,
+            "count": 333
+        },
+        "Crawler.Losses.PolicyLoss.sum": {
+            "value": 0.03242993870662758,
+            "min": 0.011323035595705733,
+            "max": 0.04382150264379258,
+            "count": 333
+        },
+        "Crawler.Losses.ValueLoss.mean": {
+            "value": 315.69726842244467,
+            "min": 0.008139611947505425,
+            "max": 739.1517125447591,
+            "count": 333
+        },
+        "Crawler.Losses.ValueLoss.sum": {
+            "value": 631.3945368448893,
+            "min": 0.0153298440699776,
+            "max": 1478.3034250895182,
+            "count": 333
+        },
+        "Crawler.Policy.LearningRate.mean": {
+            "value": 8.144497285499859e-07,
+            "min": 8.144497285499859e-07,
+            "max": 0.0002993854802048401,
+            "count": 333
+        },
+        "Crawler.Policy.LearningRate.sum": {
+            "value": 1.6288994570999717e-06,
+            "min": 1.6288994570999717e-06,
+            "max": 0.0005956972514342499,
+            "count": 333
+        },
+        "Crawler.Policy.Epsilon.mean": {
+            "value": 0.10027145000000004,
+            "min": 0.10027145000000004,
+            "max": 0.19979515999999997,
+            "count": 333
+        },
+        "Crawler.Policy.Epsilon.sum": {
+            "value": 0.20054290000000008,
+            "min": 0.10058348000000002,
+            "max": 0.39856574999999994,
+            "count": 333
+        },
+        "Crawler.Policy.Beta.mean": {
+            "value": 2.3545354999999763e-05,
+            "min": 2.3545354999999763e-05,
+            "max": 0.004989778484000002,
+            "count": 333
+        },
+        "Crawler.Policy.Beta.sum": {
+            "value": 4.7090709999999526e-05,
+            "min": 3.911565200000015e-05,
+            "max": 0.009928430924999999,
+            "count": 333
+        },
+        "Crawler.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 333
+        },
+        "Crawler.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 333
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1657940144",
+        "python_version": "3.8.13 (default, Mar 28 2022, 06:16:26) \n[Clang 12.0.0 ]",
+        "command_line_arguments": "/usr/local/Caskroom/miniconda/base/envs/ml-agents/bin/mlagents-learn ./config/ppo/Crawler.yaml --run-id=firstCrawlerRun2 --env=./trained-envs-executables/macos/crawler/crawler --no-graphics",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.1",
+        "numpy_version": "1.22.3",
+        "end_time_seconds": "1657953290"
+    },
+    "total": 13145.160775676999,
+    "count": 1,
+    "self": 2.665349953000259,
+    "children": {
+        "run_training.setup": {
+            "total": 0.12322844799999988,
+            "count": 1,
+            "self": 0.12322844799999988
+        },
+        "TrainerController.start_learning": {
+            "total": 13142.372197276,
+            "count": 1,
+            "self": 17.56792155043513,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 6.074063103,
+                    "count": 1,
+                    "self": 6.074063103
+                },
+                "TrainerController.advance": {
+                    "total": 13118.568145658564,
+                    "count": 1027807,
+                    "self": 18.8558634413057,
+                    "children": {
+                        "env_step": {
+                            "total": 7102.594597130537,
+                            "count": 1027807,
+                            "self": 6080.985495180506,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1009.4610152328596,
+                                    "count": 1027807,
+                                    "self": 69.22106638543596,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 940.2399488474236,
+                                            "count": 1000489,
+                                            "self": 107.81764790640273,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 832.4223009410209,
+                                                    "count": 1000489,
+                                                    "self": 832.4223009410209
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 12.148086717170772,
+                                    "count": 1027807,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 13108.635062904732,
+                                            "count": 1027807,
+                                            "is_parallel": true,
+                                            "self": 8061.124921998285,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0022136159999996963,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.00018154299999917356,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0020320730000005227,
+                                                            "count": 4,
+                                                            "is_parallel": true,
+                                                            "self": 0.0020320730000005227
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 5047.507927290448,
+                                                    "count": 1027807,
+                                                    "is_parallel": true,
+                                                    "self": 206.75659516771339,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 236.23360212033583,
+                                                            "count": 1027807,
+                                                            "is_parallel": true,
+                                                            "self": 236.23360212033583
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 4144.918075543047,
+                                                            "count": 1027807,
+                                                            "is_parallel": true,
+                                                            "self": 4144.918075543047
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 459.5996544593521,
+                                                            "count": 1027807,
+                                                            "is_parallel": true,
+                                                            "self": 122.03838465066355,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 337.56126980868856,
+                                                                    "count": 4111228,
+                                                                    "is_parallel": true,
+                                                                    "self": 337.56126980868856
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 5997.117685086721,
+                            "count": 1027807,
+                            "self": 27.776913906312075,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 878.6955440304173,
+                                    "count": 1027807,
+                                    "self": 875.6686419584186,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.026902071998734,
+                                            "count": 20,
+                                            "self": 3.026902071998734
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 5090.645227149992,
+                                    "count": 476,
+                                    "self": 1459.8512494169468,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 3630.7939777330453,
+                                            "count": 14280,
+                                            "self": 3630.7939777330453
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.094000253942795e-06,
+                    "count": 1,
+                    "self": 1.094000253942795e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.16206586999942374,
+                    "count": 1,
+                    "self": 0.0024772550004854565,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.15958861499893828,
+                            "count": 1,
+                            "self": 0.15958861499893828
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Crawler": {
+        "checkpoints": [
+            {
+                "steps": 8499475,
+                "file_path": "results/firstCrawlerRun2/Crawler/Crawler-8499475.onnx",
+                "reward": 3464.084716796875,
+                "creation_time": 1657951361.849535,
+                "auxillary_file_paths": [
+                    "results/firstCrawlerRun2/Crawler/Crawler-8499475.pt"
+                ]
+            },
+            {
+                "steps": 8999283,
+                "file_path": "results/firstCrawlerRun2/Crawler/Crawler-8999283.onnx",
+                "reward": null,
+                "creation_time": 1657952000.587018,
+                "auxillary_file_paths": [
+                    "results/firstCrawlerRun2/Crawler/Crawler-8999283.pt"
+                ]
+            },
+            {
+                "steps": 9499691,
+                "file_path": "results/firstCrawlerRun2/Crawler/Crawler-9499691.onnx",
+                "reward": 2414.4946995320774,
+                "creation_time": 1657952640.07986,
+                "auxillary_file_paths": [
+                    "results/firstCrawlerRun2/Crawler/Crawler-9499691.pt"
+                ]
+            },
+            {
+                "steps": 9999355,
+                "file_path": "results/firstCrawlerRun2/Crawler/Crawler-9999355.onnx",
+                "reward": 2669.618194580078,
+                "creation_time": 1657953287.142907,
+                "auxillary_file_paths": [
+                    "results/firstCrawlerRun2/Crawler/Crawler-9999355.pt"
+                ]
+            },
+            {
+                "steps": 10000355,
+                "file_path": "results/firstCrawlerRun2/Crawler/Crawler-10000355.onnx",
+                "reward": 2717.3339556525734,
+                "creation_time": 1657953287.388594,
+                "auxillary_file_paths": [
+                    "results/firstCrawlerRun2/Crawler/Crawler-10000355.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 10000355,
+            "file_path": "results/firstCrawlerRun2/Crawler.onnx",
+            "reward": 2717.3339556525734,
+            "creation_time": 1657953287.388594,
+            "auxillary_file_paths": [
+                "results/firstCrawlerRun2/Crawler/Crawler-10000355.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1"
+    }
+}