First Push`

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SoccerTwos
+      library_name: ml-agents
+---
+    
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos** 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-SoccerTwos
+  2. Step 1: Write your model_id: Harm/poca-SoccerTwos-10M
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e03192c09e5b55a709174bd9cdce81c017116da4a59dd180b160b31cd86f68
+size 1768746

SoccerTwos/SoccerTwos-3999362.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248e23754aee64f0c8f18b3c2333809f66787475f942c6c60cb9dc48505c8302
+size 1768746

SoccerTwos/SoccerTwos-3999362.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7440f8e2662ecb2492dd9a818eb974475d63e290eccdc05966b379fabf0b0383
+size 28429903

SoccerTwos/SoccerTwos-4499216.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e79aecdd652a0d120719a820a007a1d5ee49d23a32d4e90d51175115b8af7ed
+size 1768746

SoccerTwos/SoccerTwos-4499216.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9465262362138095996e5e8db29453f91bac7b4bfec0fb272dc4d4ac22195f78
+size 28429903

SoccerTwos/SoccerTwos-4999076.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0513624f1895b60164d6df7d2afb9d745ee6afb5d79b9bd684d8e9b63bca95bc
+size 1768746

SoccerTwos/SoccerTwos-4999076.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a792cd38ffe87872265c615220b7e9f05a77951e0b7316af829d58576cf1c012
+size 28429903

SoccerTwos/SoccerTwos-5499454.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bfd05b59f1e5dc0475e87c4b460493e9350353d88407a3e9132d97acb96ce31
+size 1768746

SoccerTwos/SoccerTwos-5499454.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc605d4d5074b644902198e6fb35bade66c3e6e65d8d3553ef87bc486492cf1
+size 28429903

SoccerTwos/SoccerTwos-5627454.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e03192c09e5b55a709174bd9cdce81c017116da4a59dd180b160b31cd86f68
+size 1768746

SoccerTwos/SoccerTwos-5627454.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca0b9978ab9cfe9257458d3602b6261d39cbbf79139a8be8952e00c5d647ae5b
+size 28429903

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f36d0f8a6fc45795aefebb05c223a629ec6a81de41657d8033781a497021ac9
+size 28428927

SoccerTwos/events.out.tfevents.1682599911.ZB-5CG0095CZ3.5988.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51c1ab6c55cc8f0c298b94cd1bfcd3f8d6c41351c396117fbb0e97abb8ca563
+size 1211570

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "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": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "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}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 100000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "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": "SoccerTwos-10M", "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 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    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: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    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
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 100000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.exe
+  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: SoccerTwos-10M
+  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": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.7530072927474976,
+            "min": 1.5153335332870483,
+            "max": 3.2957513332366943,
+            "count": 562
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 30684.638671875,
+            "min": 17372.4140625,
+            "max": 133188.890625,
+            "count": 562
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 442.72727272727275,
+            "max": 999.0,
+            "count": 562
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19980.0,
+            "min": 14392.0,
+            "max": 26360.0,
+            "count": 562
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1199.8792716089524,
+            "min": 1191.3747873305135,
+            "max": 1199.8821415541559,
+            "count": 113
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 2399.758543217905,
+            "min": 2382.749574661027,
+            "max": 14394.102599354906,
+            "count": 113
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 5619454.0,
+            "min": 9200.0,
+            "max": 5619454.0,
+            "count": 562
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 5619454.0,
+            "min": 9200.0,
+            "max": 5619454.0,
+            "count": 562
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 3.6033758078701794e-05,
+            "min": -0.4588257670402527,
+            "max": 0.08562135696411133,
+            "count": 562
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 0.00036033758078701794,
+            "min": -4.588257789611816,
+            "max": 1.3699417114257812,
+            "count": 562
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 3.7475030694622546e-05,
+            "min": -0.37872445583343506,
+            "max": 0.0855926051735878,
+            "count": 562
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 0.00037475029239431024,
+            "min": -3.7872445583343506,
+            "max": 1.3694816827774048,
+            "count": 562
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 562
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 562
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.0,
+            "min": -0.5454545454545454,
+            "max": 0.32797332604726154,
+            "count": 562
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 0.0,
+            "min": -6.0,
+            "max": 4.919599890708923,
+            "count": 562
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.0,
+            "min": -0.5454545454545454,
+            "max": 0.32797332604726154,
+            "count": 562
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 0.0,
+            "min": -6.0,
+            "max": 4.919599890708923,
+            "count": 562
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 562
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 562
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01523812247639095,
+            "min": 0.010124737523923007,
+            "max": 0.024689055467024445,
+            "count": 257
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01523812247639095,
+            "min": 0.010124737523923007,
+            "max": 0.024689055467024445,
+            "count": 257
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 5.359651996291367e-09,
+            "min": 1.404278090107643e-09,
+            "max": 0.007951977666622648,
+            "count": 257
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 5.359651996291367e-09,
+            "min": 1.404278090107643e-09,
+            "max": 0.007951977666622648,
+            "count": 257
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 7.776809699914603e-09,
+            "min": 1.8967375151982917e-09,
+            "max": 0.009293046900226424,
+            "count": 257
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 7.776809699914603e-09,
+            "min": 1.8967375151982917e-09,
+            "max": 0.009293046900226424,
+            "count": 257
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 257
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 257
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 257
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 257
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 257
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 257
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1682599907",
+        "python_version": "3.9.16 (main, Mar  8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\HBU1808.39421\\.conda\\envs\\hfrl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos-10M --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.0.0+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1682626712"
+    },
+    "total": 26804.6690466,
+    "count": 1,
+    "self": 0.6840587999977288,
+    "children": {
+        "run_training.setup": {
+            "total": 0.13094649999999985,
+            "count": 1,
+            "self": 0.13094649999999985
+        },
+        "TrainerController.start_learning": {
+            "total": 26803.8540413,
+            "count": 1,
+            "self": 14.14166590019886,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 7.177210200002125,
+                    "count": 28,
+                    "self": 7.177210200002125
+                },
+                "TrainerController.advance": {
+                    "total": 26782.188153699797,
+                    "count": 365965,
+                    "self": 14.75982709996606,
+                    "children": {
+                        "env_step": {
+                            "total": 11379.480486999546,
+                            "count": 365965,
+                            "self": 8785.837795099784,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2584.2824252000487,
+                                    "count": 365965,
+                                    "self": 87.59324310027068,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2496.689182099778,
+                                            "count": 726662,
+                                            "self": 2496.689182099778
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 9.36026669971396,
+                                    "count": 365964,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 26779.30251230026,
+                                            "count": 365964,
+                                            "is_parallel": true,
+                                            "self": 19725.317573300093,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.09141170000155219,
+                                                    "count": 56,
+                                                    "is_parallel": true,
+                                                    "self": 0.017937900010898566,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.07347379999065362,
+                                                            "count": 224,
+                                                            "is_parallel": true,
+                                                            "self": 0.07347379999065362
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 7053.893527300164,
+                                                    "count": 365964,
+                                                    "is_parallel": true,
+                                                    "self": 386.408833898543,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 298.76427030093015,
+                                                            "count": 365964,
+                                                            "is_parallel": true,
+                                                            "self": 298.76427030093015
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 5092.0302624005535,
+                                                            "count": 365964,
+                                                            "is_parallel": true,
+                                                            "self": 5092.0302624005535
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1276.6901607001375,
+                                                            "count": 731928,
+                                                            "is_parallel": true,
+                                                            "self": 244.83094719978112,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1031.8592135003564,
+                                                                    "count": 2927712,
+                                                                    "is_parallel": true,
+                                                                    "self": 1031.8592135003564
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 15387.947839600287,
+                            "count": 365964,
+                            "self": 96.26984210020419,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 2154.12127770009,
+                                    "count": 365964,
+                                    "self": 2150.8659975000855,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.255280200004563,
+                                            "count": 11,
+                                            "self": 3.255280200004563
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 13137.556719799994,
+                                    "count": 258,
+                                    "self": 1280.481288900055,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 11857.075430899939,
+                                            "count": 7740,
+                                            "self": 11857.075430899939
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.8000031306874007e-06,
+                    "count": 1,
+                    "self": 2.8000031306874007e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.3470086999986961,
+                    "count": 1,
+                    "self": 0.007350699997914489,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.3396580000007816,
+                            "count": 1,
+                            "self": 0.3396580000007816
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 3999362,
+                "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-3999362.onnx",
+                "reward": 0.0,
+                "creation_time": 1682618144.0289497,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-3999362.pt"
+                ]
+            },
+            {
+                "steps": 4499216,
+                "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-4499216.onnx",
+                "reward": 0.0,
+                "creation_time": 1682620396.255104,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-4499216.pt"
+                ]
+            },
+            {
+                "steps": 4999076,
+                "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-4999076.onnx",
+                "reward": 0.0,
+                "creation_time": 1682622663.9818969,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-4999076.pt"
+                ]
+            },
+            {
+                "steps": 5499454,
+                "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5499454.onnx",
+                "reward": 0.0,
+                "creation_time": 1682625923.34515,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5499454.pt"
+                ]
+            },
+            {
+                "steps": 5627454,
+                "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5627454.onnx",
+                "reward": 0.0,
+                "creation_time": 1682626711.4336407,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5627454.pt"
+                ]
+            }
+        ],
+        "elo": 1200.1285520530978,
+        "final_checkpoint": {
+            "steps": 5627454,
+            "file_path": "results\\SoccerTwos-10M\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1682626711.4336407,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5627454.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.0+cpu"
+    }
+}