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: jrnold/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:b6d47e680afa63d937587db75c361afabdec858097ba729ce7f2db3a81f0763b
+size 1763220

SoccerTwos/SoccerTwos-15566.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d47e680afa63d937587db75c361afabdec858097ba729ce7f2db3a81f0763b
+size 1763220

SoccerTwos/SoccerTwos-15566.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b18dee2d7949cbb22360e6e480296782ddb38464d5a4560f2ab3706fbc5ac9
+size 9479511

SoccerTwos/SoccerTwos-16999918.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1370b003ec759dd4ba55438bc9251acd64b7fbf0c159f143afa56beafcbd573f
+size 1763220

SoccerTwos/SoccerTwos-16999918.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba73348d6a4c2b052958534e84e20aa1d14c1d08831fb38989d178c0f315123a
+size 28424007

SoccerTwos/SoccerTwos-17499910.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8042b167e2205cb6b860b9013004f35ddaa16e6a0d69423b9fd7484a2d071c7f
+size 1763220

SoccerTwos/SoccerTwos-17499910.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a424fd7a09b9bbb1292a222ec41a6f4d75069202bc1f57c6ee6c0fd3ebbd7213
+size 28424007

SoccerTwos/SoccerTwos-17999975.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca0d1158edfa06ca491324376d2788ccd8bca09a42460a44800b163a38e84a02
+size 1763220

SoccerTwos/SoccerTwos-17999975.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2566f88f032f43498d6c8dc1e1164522aa9d72a640ea3b9f9e76c1216010e950
+size 28424007

SoccerTwos/SoccerTwos-18499994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923ddff90c7abb93a9144b40f39c9a943330d5e41451baefa34ab5d24bd123fe
+size 1763220

SoccerTwos/SoccerTwos-18499994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a589953efc4b0a206e424e90a72681221d405fc6beb7ef413adcebea94f822
+size 28424007

SoccerTwos/SoccerTwos-18999990.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c53d93431c7b9831c39262fb3b91c5e61ebedbe5109f1c6de6b3ff234a668c
+size 1763220

SoccerTwos/SoccerTwos-18999990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da0003bc56cede23b045693cc236c6c0db1b1495fa99d4e545e7b358b9c3039
+size 28424007

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da0003bc56cede23b045693cc236c6c0db1b1495fa99d4e545e7b358b9c3039
+size 28424007

SoccerTwos/events.out.tfevents.1675834640.Jeffreys-MacBook-Pro-2.local.21533.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994f5ce451658588bd6e055a05f01beabb99c207d5427123f1414c718107e7d8
+size 19756895

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": 10000, "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/SoccerTwos.app", "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 +1,82 @@
+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: 10000
+    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/SoccerTwos.app
+  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 +1,277 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.295684576034546,
+            "min": 3.295684576034546,
+            "max": 3.295684576034546,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 105461.90625,
+            "min": 105461.90625,
+            "max": 105461.90625,
+            "count": 1
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 971.875,
+            "min": 971.875,
+            "max": 971.875,
+            "count": 1
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 31100.0,
+            "min": 31100.0,
+            "max": 31100.0,
+            "count": 1
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1200.7492804441454,
+            "min": 1200.7492804441454,
+            "max": 1200.7492804441454,
+            "count": 1
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 2401.4985608882907,
+            "min": 2401.4985608882907,
+            "max": 2401.4985608882907,
+            "count": 1
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 9566.0,
+            "min": 9566.0,
+            "max": 9566.0,
+            "count": 1
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 9566.0,
+            "min": 9566.0,
+            "max": 9566.0,
+            "count": 1
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.007814358919858932,
+            "min": -0.007814358919858932,
+            "max": -0.007814358919858932,
+            "count": 1
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.07814358919858932,
+            "min": -0.07814358919858932,
+            "max": -0.07814358919858932,
+            "count": 1
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.007726958952844143,
+            "min": -0.007726958952844143,
+            "max": -0.007726958952844143,
+            "count": 1
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.07726959139108658,
+            "min": -0.07726959139108658,
+            "max": -0.07726959139108658,
+            "count": 1
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.04343999922275543,
+            "min": 0.04343999922275543,
+            "max": 0.04343999922275543,
+            "count": 1
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 0.4343999922275543,
+            "min": 0.4343999922275543,
+            "max": 0.4343999922275543,
+            "count": 1
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.04343999922275543,
+            "min": 0.04343999922275543,
+            "max": 0.04343999922275543,
+            "count": 1
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 0.4343999922275543,
+            "min": 0.4343999922275543,
+            "max": 0.4343999922275543,
+            "count": 1
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675834207",
+        "python_version": "3.8.16 (default, Jan 17 2023, 16:42:09) \n[Clang 14.0.6 ]",
+        "command_line_arguments": "/Users/jrnold/.pyenv/versions/mambaforge/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.1",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1675834231"
+    },
+    "total": 24.360340010999998,
+    "count": 1,
+    "self": 0.39096425700000026,
+    "children": {
+        "run_training.setup": {
+            "total": 0.062021694000000016,
+            "count": 1,
+            "self": 0.062021694000000016
+        },
+        "TrainerController.start_learning": {
+            "total": 23.90735406,
+            "count": 1,
+            "self": 0.02115698399999033,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.128362879,
+                    "count": 1,
+                    "self": 4.128362879
+                },
+                "TrainerController.advance": {
+                    "total": 19.576662858000006,
+                    "count": 1001,
+                    "self": 0.02241945900000175,
+                    "children": {
+                        "env_step": {
+                            "total": 14.936388841999996,
+                            "count": 1001,
+                            "self": 12.088677863999937,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2.8336093740000132,
+                                    "count": 1001,
+                                    "self": 0.11841361199992662,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2.7151957620000866,
+                                            "count": 2000,
+                                            "self": 2.7151957620000866
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.014101604000046564,
+                                    "count": 1001,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 15.600958393999996,
+                                            "count": 1001,
+                                            "is_parallel": true,
+                                            "self": 5.729921020999935,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.003751954999999363,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.0006619229999991205,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0030900320000002424,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0030900320000002424
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 9.867285418000062,
+                                                    "count": 1001,
+                                                    "is_parallel": true,
+                                                    "self": 0.5009040660000927,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.3315615400000018,
+                                                            "count": 1001,
+                                                            "is_parallel": true,
+                                                            "self": 0.3315615400000018
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 7.466221223999969,
+                                                            "count": 1001,
+                                                            "is_parallel": true,
+                                                            "self": 7.466221223999969
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1.5685985879999995,
+                                                            "count": 2002,
+                                                            "is_parallel": true,
+                                                            "self": 0.31877567899988346,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1.249822909000116,
+                                                                    "count": 8008,
+                                                                    "is_parallel": true,
+                                                                    "self": 1.249822909000116
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 4.617854557000007,
+                            "count": 1001,
+                            "self": 0.10161975499998288,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 4.5162348020000245,
+                                    "count": 1001,
+                                    "self": 4.5162348020000245
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0560000021087035e-06,
+                    "count": 1,
+                    "self": 1.0560000021087035e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.18117028300000015,
+                    "count": 1,
+                    "self": 0.0015677130000000261,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.17960257000000013,
+                            "count": 1,
+                            "self": 0.17960257000000013
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 1200.9985608882907,
+        "checkpoints": [
+            {
+                "steps": 15566,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15566.onnx",
+                "reward": 0.0,
+                "creation_time": 1675834231.506451,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15566.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 15566,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1675834231.506451,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-15566.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.8.1"
+    }
+}