First Push`

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **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://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: Wajid333/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:c04dc29fa8193889b14a299d4dcf526cf34816eb279c8168f7d653151d72b5f2
+size 1768747

SoccerTwos/SoccerTwos-28999152.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f627706d3104e655a1393f9f8d95317c5962839c3566b950819c8ac541bbad21
+size 1768747

SoccerTwos/SoccerTwos-28999152.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b30ac42718a3f8e9a5ab3034c5af14d4e67288572f43c453feae2ab09376c73
+size 28430482

SoccerTwos/SoccerTwos-29499543.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ddf8c3ba1eaf45b917911e6ffec7adfb27f7b71f6759da739f079207a61ab58
+size 1768747

SoccerTwos/SoccerTwos-29499543.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2267692ebe6626c6deada096bc1d20906d2eb0f01cc6faec7725611ef85f01
+size 28430482

SoccerTwos/SoccerTwos-29999352.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634978034ee45fed24ab9072aac49dcb8b30ed4faee525a42ee1e8f9f9128c0e
+size 1768747

SoccerTwos/SoccerTwos-29999352.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3345ece9497ec7f17afbdcf3d04d8c1ef604a68266b37f7df5fbeb73e22608e8
+size 28430482

SoccerTwos/SoccerTwos-30499668.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04dc29fa8193889b14a299d4dcf526cf34816eb279c8168f7d653151d72b5f2
+size 1768747

SoccerTwos/SoccerTwos-30499668.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73fbd069fd580cea72c05348475c1c52e478c4016029e08d9090fa823df73e29
+size 28430482

SoccerTwos/SoccerTwos-30504668.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04dc29fa8193889b14a299d4dcf526cf34816eb279c8168f7d653151d72b5f2
+size 1768747

SoccerTwos/SoccerTwos-30504668.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457e022838520d309678c630984e7ca260f995737371c236358a1467ea3bc375
+size 28430482

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb521bf1cb10c0bcf2b1adef356dfa51a9b74059b20fb4e3aefe44ada08d9559
+size 28429366

SoccerTwos/events.out.tfevents.1707909207.DESKTOP-PCVNORB.7792.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece8e6de33e5da84c13bb375d5df59bb58d2a2a35a6a98e10476e68e9a6d9573
+size 7612627

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": 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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "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 +1,84 @@
+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: 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
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  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": 3.1090173721313477,
+            "min": 1.9680967330932617,
+            "max": 3.2957119941711426,
+            "count": 3050
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 69542.5,
+            "min": 7779.02392578125,
+            "max": 139825.21875,
+            "count": 3050
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 432.09090909090907,
+            "max": 999.0,
+            "count": 3050
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19980.0,
+            "min": 4212.0,
+            "max": 30640.0,
+            "count": 3050
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1106.394028371355,
+            "min": 1105.7761543980168,
+            "max": 1202.6779590037042,
+            "count": 834
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 4425.57611348542,
+            "min": 2211.5523087960337,
+            "max": 16433.644009425647,
+            "count": 834
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 30499668.0,
+            "min": 9338.0,
+            "max": 30499668.0,
+            "count": 3050
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 30499668.0,
+            "min": 9338.0,
+            "max": 30499668.0,
+            "count": 3050
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.001142252003774047,
+            "min": -0.06821022182703018,
+            "max": 0.029490983113646507,
+            "count": 3050
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 0.011422519572079182,
+            "min": -1.023153305053711,
+            "max": 0.29490983486175537,
+            "count": 3050
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.0011270389659330249,
+            "min": -0.06816212832927704,
+            "max": 0.026077916845679283,
+            "count": 3050
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 0.011270389892160892,
+            "min": -1.0224319696426392,
+            "max": 0.26077917218208313,
+            "count": 3050
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 3050
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 3050
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.0,
+            "min": -0.7692307692307693,
+            "max": 0.3462000002463659,
+            "count": 3050
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 0.0,
+            "min": -10.307600021362305,
+            "max": 6.134799897670746,
+            "count": 3050
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.0,
+            "min": -0.7692307692307693,
+            "max": 0.3462000002463659,
+            "count": 3050
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 0.0,
+            "min": -10.307600021362305,
+            "max": 6.134799897670746,
+            "count": 3050
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3050
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3050
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01199939750416282,
+            "min": 0.009683321138921504,
+            "max": 0.0247808082223249,
+            "count": 1405
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01199939750416282,
+            "min": 0.009683321138921504,
+            "max": 0.0247808082223249,
+            "count": 1405
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 1.6804577107620845e-08,
+            "min": 1.6066720870400175e-10,
+            "max": 0.024891944141461262,
+            "count": 1405
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 1.6804577107620845e-08,
+            "min": 1.6066720870400175e-10,
+            "max": 0.024891944141461262,
+            "count": 1405
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 1.6932955807883825e-08,
+            "min": 1.881779200056203e-10,
+            "max": 0.025511121548364338,
+            "count": 1405
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 1.6932955807883825e-08,
+            "min": 1.881779200056203e-10,
+            "max": 0.025511121548364338,
+            "count": 1405
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1405
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1405
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 1405
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 1405
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 1405
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 1405
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1707909201",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\WajidIQBAL\\anaconda3\\envs\\rlll\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.0+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1707970458"
+    },
+    "total": 61257.0453976,
+    "count": 1,
+    "self": 0.4663060000020778,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05751190000000861,
+            "count": 1,
+            "self": 0.05751190000000861
+        },
+        "TrainerController.start_learning": {
+            "total": 61256.5215797,
+            "count": 1,
+            "self": 29.80428909652983,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 13.804234599957908,
+                    "count": 152,
+                    "self": 13.804234599957908
+                },
+                "TrainerController.advance": {
+                    "total": 61212.81467410352,
+                    "count": 1983824,
+                    "self": 31.51725379947311,
+                    "children": {
+                        "env_step": {
+                            "total": 20554.860432702186,
+                            "count": 1983824,
+                            "self": 16081.39585360005,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 4453.426088601476,
+                                    "count": 1983824,
+                                    "self": 183.04756110322342,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 4270.378527498253,
+                                            "count": 3941154,
+                                            "self": 4270.378527498253
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 20.038490500658554,
+                                    "count": 1983823,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 61217.14689130344,
+                                            "count": 1983823,
+                                            "is_parallel": true,
+                                            "self": 48596.32925790934,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.17005310006243235,
+                                                    "count": 304,
+                                                    "is_parallel": true,
+                                                    "self": 0.031948700181146705,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.13810439988128564,
+                                                            "count": 1216,
+                                                            "is_parallel": true,
+                                                            "self": 0.13810439988128564
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 12620.647580294037,
+                                                    "count": 1983823,
+                                                    "is_parallel": true,
+                                                    "self": 748.5680125834697,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 504.62159380177127,
+                                                            "count": 1983823,
+                                                            "is_parallel": true,
+                                                            "self": 504.62159380177127
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 9258.36415170342,
+                                                            "count": 1983823,
+                                                            "is_parallel": true,
+                                                            "self": 9258.36415170342
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 2109.0938222053783,
+                                                            "count": 3967646,
+                                                            "is_parallel": true,
+                                                            "self": 388.4085669996657,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1720.6852552057126,
+                                                                    "count": 15870584,
+                                                                    "is_parallel": true,
+                                                                    "self": 1720.6852552057126
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 40626.43698760187,
+                            "count": 1983823,
+                            "self": 241.9663722038531,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3534.66847819801,
+                                    "count": 1983823,
+                                    "self": 3529.1874535979873,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 5.481024600022465,
+                                            "count": 61,
+                                            "self": 5.481024600022465
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 36849.80213720001,
+                                    "count": 1405,
+                                    "self": 2789.5615048997497,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 34060.24063230026,
+                                            "count": 42165,
+                                            "self": 34060.24063230026
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0999938240274787e-06,
+                    "count": 1,
+                    "self": 1.0999938240274787e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09838079999462934,
+                    "count": 1,
+                    "self": 0.0073776999925030395,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0910031000021263,
+                            "count": 1,
+                            "self": 0.0910031000021263
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 28999152,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-28999152.onnx",
+                "reward": 0.0,
+                "creation_time": 1707966345.4605298,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-28999152.pt"
+                ]
+            },
+            {
+                "steps": 29499543,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29499543.onnx",
+                "reward": 0.0,
+                "creation_time": 1707967671.520455,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29499543.pt"
+                ]
+            },
+            {
+                "steps": 29999352,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29999352.onnx",
+                "reward": 0.0,
+                "creation_time": 1707969033.0221674,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29999352.pt"
+                ]
+            },
+            {
+                "steps": 30499668,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30499668.onnx",
+                "reward": 0.0,
+                "creation_time": 1707970454.8388364,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30499668.pt"
+                ]
+            },
+            {
+                "steps": 30504668,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30504668.onnx",
+                "reward": 0.0,
+                "creation_time": 1707970458.4303687,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30504668.pt"
+                ]
+            }
+        ],
+        "elo": 1106.8989734668996,
+        "final_checkpoint": {
+            "steps": 30504668,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1707970458.4303687,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30504668.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.0+cpu"
+    }
+}