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: JoBuettner/poca-SoccerTwos
+  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 sha256:1251d2ea42a7531014f41f51782edd7f4f29f0adb4202e5c16ee18b31758b9a2
+size 1768747

SoccerTwos/SoccerTwos-16999758.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a108cf7b4f83b8aacebbbcd8108234d5af78b2769bd9e68f4f18faa357b2b41b
+size 1768747

SoccerTwos/SoccerTwos-16999758.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a055099eaf7645b50f14c95c3ff698a739a235f5c77ca9a0e31eb3fb748ce108
+size 28430025

SoccerTwos/SoccerTwos-17499362.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:735484ccb59e530987562eb09f52b91ea7656c5e9e4074fdefdf7c1431c482b5
+size 1768747

SoccerTwos/SoccerTwos-17499362.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38682901875dc527dea757f1330105d7470408f7b7e82a9ecb989d0aa3946a3a
+size 28430025

SoccerTwos/SoccerTwos-17999098.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a553e06a91c13a419cc2f575a3737f4cc7e5ccf6187278824a705302569e85e
+size 1768747

SoccerTwos/SoccerTwos-17999098.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0316433429abbbb22b6426b4f9a29edee9d3355f52d484c8e5304b53203d16
+size 28430025

SoccerTwos/SoccerTwos-18499702.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf84907c766ef87ed87889a5e30bb3c339c3d4485ce40a4aecb472755736430
+size 1768747

SoccerTwos/SoccerTwos-18499702.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44027caab51636b8f13e48a7ea31ccad740b38093f6d0554ea14c192b5318aa6
+size 28430025

SoccerTwos/SoccerTwos-18630702.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1251d2ea42a7531014f41f51782edd7f4f29f0adb4202e5c16ee18b31758b9a2
+size 1768747

SoccerTwos/SoccerTwos-18630702.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25cc2196878f2d7e707ea4ec1c7e813ff12448c2df7ff570a11ff60ec25aa601
+size 28430025

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067458abfa4fe3a7187ca2cb62b5e934e809a1f8c7c05801bc498412ad97587d
+size 28428927

SoccerTwos/events.out.tfevents.1684099444.DESKTOP-M2HS072.18156.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3771d5c233ddb9527835baf6d1cc093c2115545ebb4131154c9e9ccf291377d
+size 3091205

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"}, "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, "checkpoint_interval": 500000, "max_steps": 50000000, "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", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,81 @@
+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
+    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
+    checkpoint_interval: 500000
+    max_steps: 50000000
+    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
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/timers.json

@@ -0,0 +1,375 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.954332947731018,
+            "min": 1.3264840841293335,
+            "max": 3.295761823654175,
+            "count": 1863
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 37022.8828125,
+            "min": 13968.203125,
+            "max": 119658.234375,
+            "count": 1863
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 407.6666666666667,
+            "max": 999.0,
+            "count": 1863
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19980.0,
+            "min": 4120.0,
+            "max": 29364.0,
+            "count": 1863
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1193.01010444665,
+            "min": 1183.7567493884217,
+            "max": 1211.300011561075,
+            "count": 221
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 2386.0202088933,
+            "min": 2368.8649997466773,
+            "max": 14529.666804347418,
+            "count": 221
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 18629702.0,
+            "min": 9616.0,
+            "max": 18629702.0,
+            "count": 1863
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 18629702.0,
+            "min": 9616.0,
+            "max": 18629702.0,
+            "count": 1863
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -1.111352389671083e-06,
+            "min": -0.044144924730062485,
+            "max": 0.018055004999041557,
+            "count": 1863
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -1.1113524124084506e-05,
+            "min": -0.662173867225647,
+            "max": 0.25595420598983765,
+            "count": 1863
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -3.35992376676586e-06,
+            "min": -0.04418877512216568,
+            "max": 0.01754818670451641,
+            "count": 1863
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -3.359923721291125e-05,
+            "min": -0.6628316044807434,
+            "max": 0.2481795847415924,
+            "count": 1863
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1863
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1863
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.0,
+            "min": -0.5,
+            "max": 0.3054000011512211,
+            "count": 1863
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 0.0,
+            "min": -8.0,
+            "max": 4.275600016117096,
+            "count": 1863
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.0,
+            "min": -0.5,
+            "max": 0.3054000011512211,
+            "count": 1863
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 0.0,
+            "min": -8.0,
+            "max": 4.275600016117096,
+            "count": 1863
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1863
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1863
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01567243464984737,
+            "min": 0.010860774454098039,
+            "max": 0.027968196836688244,
+            "count": 851
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01567243464984737,
+            "min": 0.010860774454098039,
+            "max": 0.027968196836688244,
+            "count": 851
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 3.425246914804762e-11,
+            "min": 2.3595142737790433e-11,
+            "max": 0.005436938970039288,
+            "count": 851
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 3.425246914804762e-11,
+            "min": 2.3595142737790433e-11,
+            "max": 0.005436938970039288,
+            "count": 851
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 4.56346413204208e-11,
+            "min": 3.366520314832903e-11,
+            "max": 0.005439961049705744,
+            "count": 851
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 4.56346413204208e-11,
+            "min": 3.366520314832903e-11,
+            "max": 0.005439961049705744,
+            "count": 851
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 851
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 851
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 851
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 851
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 851
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 851
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1684099442",
+        "python_version": "3.7.9 (tags/v3.7.9:13c94747c7, Aug 17 2020, 18:58:18) [MSC v.1900 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\johbu\\AppData\\Local\\Programs\\Python\\Python37\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=.\\training-envs-executables\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.13.1+cpu",
+        "numpy_version": "1.21.6",
+        "end_time_seconds": "1684141538"
+    },
+    "total": 42095.9810893,
+    "count": 1,
+    "self": 0.40295310000510653,
+    "children": {
+        "run_training.setup": {
+            "total": 0.07414120000000013,
+            "count": 1,
+            "self": 0.07414120000000013
+        },
+        "TrainerController.start_learning": {
+            "total": 42095.503995,
+            "count": 1,
+            "self": 14.704631397704361,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 8.012174899989207,
+                    "count": 93,
+                    "self": 8.012174899989207
+                },
+                "TrainerController.advance": {
+                    "total": 42072.67401290231,
+                    "count": 1217474,
+                    "self": 15.07942959882348,
+                    "children": {
+                        "env_step": {
+                            "total": 13986.828992203496,
+                            "count": 1217474,
+                            "self": 11024.74603840562,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2952.9800428989524,
+                                    "count": 1217474,
+                                    "self": 85.42414060606143,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2867.555902292891,
+                                            "count": 2417620,
+                                            "self": 391.39378209354527,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 2476.1621201993457,
+                                                    "count": 2417620,
+                                                    "self": 2476.1621201993457
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 9.102910898924563,
+                                    "count": 1217474,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 42069.48677810002,
+                                            "count": 1217474,
+                                            "is_parallel": true,
+                                            "self": 33182.724791397326,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.13034849997127318,
+                                                    "count": 186,
+                                                    "is_parallel": true,
+                                                    "self": 0.029093799915881124,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.10125470005539206,
+                                                            "count": 744,
+                                                            "is_parallel": true,
+                                                            "self": 0.10125470005539206
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 8886.63163820272,
+                                                    "count": 1217474,
+                                                    "is_parallel": true,
+                                                    "self": 504.76745889585254,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 474.3629797996917,
+                                                            "count": 1217474,
+                                                            "is_parallel": true,
+                                                            "self": 474.3629797996917
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 6278.15898090307,
+                                                            "count": 1217474,
+                                                            "is_parallel": true,
+                                                            "self": 6278.15898090307
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1629.3422186041057,
+                                                            "count": 2434948,
+                                                            "is_parallel": true,
+                                                            "self": 348.5505115046576,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1280.791707099448,
+                                                                    "count": 9739792,
+                                                                    "is_parallel": true,
+                                                                    "self": 1280.791707099448
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 28070.76559109999,
+                            "count": 1217474,
+                            "self": 157.3080017994107,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3583.9044986006,
+                                    "count": 1217474,
+                                    "self": 3580.662047500574,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.2424511000260736,
+                                            "count": 37,
+                                            "self": 3.2424511000260736
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 24329.553090699977,
+                                    "count": 851,
+                                    "self": 1843.207980099789,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 22486.34511060019,
+                                            "count": 25542,
+                                            "self": 22486.34511060019
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.999988156370819e-07,
+                    "count": 1,
+                    "self": 7.999988156370819e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.11317499999859137,
+                    "count": 1,
+                    "self": 0.029603699993458577,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0835713000051328,
+                            "count": 1,
+                            "self": 0.0835713000051328
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 16999758,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-16999758.onnx",
+                "reward": 0.0,
+                "creation_time": 1684137871.4929845,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-16999758.pt"
+                ]
+            },
+            {
+                "steps": 17499362,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-17499362.onnx",
+                "reward": 0.0,
+                "creation_time": 1684138996.7285898,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-17499362.pt"
+                ]
+            },
+            {
+                "steps": 17999098,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-17999098.onnx",
+                "reward": 0.0,
+                "creation_time": 1684140098.2895796,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-17999098.pt"
+                ]
+            },
+            {
+                "steps": 18499702,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18499702.onnx",
+                "reward": 0.0,
+                "creation_time": 1684141242.3639696,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18499702.pt"
+                ]
+            },
+            {
+                "steps": 18630702,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18630702.onnx",
+                "reward": 0.0,
+                "creation_time": 1684141538.436475,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18630702.pt"
+                ]
+            }
+        ],
+        "elo": 1193.01010444665,
+        "final_checkpoint": {
+            "steps": 18630702,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1684141538.436475,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18630702.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.13.1+cpu"
+    }
+}