Upload 17 files

Agent.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a542512c76547f60d4b0d63c16417783ec7eea886633dd6e596826e28e5e56
+size 21336

Agent/Agent-6498432.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d4a0bd11b24596f427d1f434f44af4303b666b8f8132a81d08148aef5b7162
+size 21336

Agent/Agent-6498432.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc66534500ddfcf747a1e22aefdaa1e49a546619ad0b39f4dd58c3416f48b5a3
+size 129607

Agent/Agent-6999096.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3848a882eccc17dccc1a2e2b332856b25b01a6184fcb3e42fb2c5ce357032a
+size 21336

Agent/Agent-6999096.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:757f120d4a00dc7d0b6bf95efac327d69f4fc9c6311c6685496a1865e4980ee0
+size 129607

Agent/Agent-7498432.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c26f4001460fb5ffb20f9a9856abfae3cbc2df506cf17fb4683e444fb7ba936
+size 21336

Agent/Agent-7498432.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c36623b618bb423c3027292a8370430bbb17e2c56f490ee2f7220fb530fdad0
+size 129607

Agent/Agent-7999096.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8865d3953e862153f9b6024711bb91836855142fdfd2838ea1bb1ae20fcc9b80
+size 21336

Agent/Agent-7999096.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b434751bd9ac86bc341888ff4172ce765bc7917432680478ed6262bade6188b
+size 129607

Agent/Agent-8016384.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a542512c76547f60d4b0d63c16417783ec7eea886633dd6e596826e28e5e56
+size 21336

Agent/Agent-8016384.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729a5aa675da7ca384465b33d7ebe236752ed8b39891769c4f926650eec18b87
+size 129607

Agent/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729a5aa675da7ca384465b33d7ebe236752ed8b39891769c4f926650eec18b87
+size 129607

Agent/events.out.tfevents.1715265317.RICHARD.29428.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f7b62087d2b816e4c09ccebb74dd2316a8a4830c361fe0ccda58432a13e361a
+size 229967

README.md

@@ -0,0 +1,29 @@
+---
+library_name: hivex
+original_train_name: WindFarmControl_pattern_6_task_0_run_id_1_train
+tags:
+- hivex
+- hivex-wind-farm-control
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-WFC-PPO-baseline-task-0-pattern-6
+  results:
+  - task:
+      type: main-task
+      name: main_task
+      task-id: 0
+      pattern-id: 6
+    dataset:
+      name: hivex-wind-farm-control
+      type: hivex-wind-farm-control
+    metrics:
+    - type: cumulative_reward
+      value: 4597.647395019531 +/- 42.54293382504652
+      name: Cumulative Reward
+      verified: true
+    - type: individual_performance
+      value: 4597.578510742187 +/- 43.53561804434955
+      name: Individual Performance
+      verified: true
+---

configuration.yaml

@@ -0,0 +1,94 @@
+default_settings: null
+behaviors:
+  Agent:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 256
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 64
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.9
+        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: 8000000
+    time_horizon: 2048
+    summary_freq: 40000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/dev_environments/Hivex_WindFarmControl_win
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: 5000
+  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:
+  pattern:
+    curriculum:
+    - value:
+        sampler_type: constant
+        sampler_parameters:
+          seed: 5000
+          value: 6
+      name: pattern
+      completion_criteria: null
+  task:
+    curriculum:
+    - value:
+        sampler_type: constant
+        sampler_parameters:
+          seed: 5001
+          value: 0
+      name: task
+      completion_criteria: null
+checkpoint_settings:
+  run_id: WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train
+  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 +1,371 @@
+{
+    "name": "root",
+    "gauges": {
+        "Agent.Policy.Entropy.mean": {
+            "value": 1.0538036823272705,
+            "min": 0.8161932826042175,
+            "max": 1.0959194898605347,
+            "count": 200
+        },
+        "Agent.Policy.Entropy.sum": {
+            "value": 42152.1484375,
+            "min": 32641.201171875,
+            "max": 43915.6875,
+            "count": 200
+        },
+        "Agent.Environment.LessonNumber.pattern.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 200
+        },
+        "Agent.Environment.LessonNumber.pattern.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 200
+        },
+        "Agent.Environment.LessonNumber.task.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 200
+        },
+        "Agent.Environment.LessonNumber.task.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 200
+        },
+        "Agent.Step.mean": {
+            "value": 7999096.0,
+            "min": 39096.0,
+            "max": 7999096.0,
+            "count": 200
+        },
+        "Agent.Step.sum": {
+            "value": 7999096.0,
+            "min": 39096.0,
+            "max": 7999096.0,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 9.070965766906738,
+            "min": 0.40659329295158386,
+            "max": 9.580119132995605,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 217.7031707763672,
+            "min": 9.758238792419434,
+            "max": 229.92286682128906,
+            "count": 200
+        },
+        "Agent.Losses.PolicyLoss.mean": {
+            "value": 0.04760897559130431,
+            "min": 0.04352403412370237,
+            "max": 0.05461486716607367,
+            "count": 200
+        },
+        "Agent.Losses.PolicyLoss.sum": {
+            "value": 0.14282692677391293,
+            "min": 0.10052567585807992,
+            "max": 0.16384460149822103,
+            "count": 200
+        },
+        "Agent.Losses.ValueLoss.mean": {
+            "value": 0.24837617975075746,
+            "min": 0.06441270624377972,
+            "max": 1.6263256006253262,
+            "count": 200
+        },
+        "Agent.Losses.ValueLoss.sum": {
+            "value": 0.7451285392522724,
+            "min": 0.19323811873133914,
+            "max": 3.2526512012506523,
+            "count": 200
+        },
+        "Agent.Policy.LearningRate.mean": {
+            "value": 8.856997047999973e-07,
+            "min": 8.856997047999973e-07,
+            "max": 0.00029907840030719997,
+            "count": 200
+        },
+        "Agent.Policy.LearningRate.sum": {
+            "value": 2.657099114399992e-06,
+            "min": 2.657099114399992e-06,
+            "max": 0.0008936568021144,
+            "count": 200
+        },
+        "Agent.Policy.Epsilon.mean": {
+            "value": 0.10029520000000001,
+            "min": 0.10029520000000001,
+            "max": 0.1996928,
+            "count": 200
+        },
+        "Agent.Policy.Epsilon.sum": {
+            "value": 0.30088560000000003,
+            "min": 0.30088560000000003,
+            "max": 0.5978856,
+            "count": 200
+        },
+        "Agent.Policy.Beta.mean": {
+            "value": 2.4730479999999958e-05,
+            "min": 2.4730479999999958e-05,
+            "max": 0.004984670720000001,
+            "count": 200
+        },
+        "Agent.Policy.Beta.sum": {
+            "value": 7.419143999999988e-05,
+            "min": 7.419143999999988e-05,
+            "max": 0.014894491440000001,
+            "count": 200
+        },
+        "Agent.Environment.EpisodeLength.mean": {
+            "value": 4999.0,
+            "min": 4999.0,
+            "max": 4999.0,
+            "count": 200
+        },
+        "Agent.Environment.EpisodeLength.sum": {
+            "value": 39992.0,
+            "min": 39992.0,
+            "max": 39992.0,
+            "count": 200
+        },
+        "Agent.WindFarmControl.IndividualPerformance.mean": {
+            "value": 4535.950012207031,
+            "min": 109.12000713031739,
+            "max": 4682.008117675781,
+            "count": 200
+        },
+        "Agent.WindFarmControl.IndividualPerformance.sum": {
+            "value": 36287.60009765625,
+            "min": 872.9600570425391,
+            "max": 37456.06494140625,
+            "count": 200
+        },
+        "Agent.Environment.CumulativeReward.mean": {
+            "value": 4534.995567321777,
+            "min": 183.15793666518283,
+            "max": 4664.359016418457,
+            "count": 200
+        },
+        "Agent.Environment.CumulativeReward.sum": {
+            "value": 36279.96453857422,
+            "min": 1465.2634933214626,
+            "max": 37314.872131347656,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicReward.mean": {
+            "value": 4534.995567321777,
+            "min": 183.15793666518283,
+            "max": 4664.359016418457,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicReward.sum": {
+            "value": 36279.96453857422,
+            "min": 1465.2634933214626,
+            "max": 37314.872131347656,
+            "count": 200
+        },
+        "Agent.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "Agent.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1715265317",
+        "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\pdsie\\anaconda3\\envs\\mlagents20\\Scripts\\mlagents-learn c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/configs/mlagents/tmp/train/WindFarmControl_pattern_6_task_0_run_id_1_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train",
+        "mlagents_version": "0.30.0",
+        "mlagents_envs_version": "0.30.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.7.1+cu110",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1715269260"
+    },
+    "total": 3943.4078246000004,
+    "count": 1,
+    "self": 0.16108900000017456,
+    "children": {
+        "run_training.setup": {
+            "total": 0.04457129999999998,
+            "count": 1,
+            "self": 0.04457129999999998
+        },
+        "TrainerController.start_learning": {
+            "total": 3943.2021643000003,
+            "count": 1,
+            "self": 10.747027800163323,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.6132256999999999,
+                    "count": 1,
+                    "self": 1.6132256999999999
+                },
+                "TrainerController.advance": {
+                    "total": 3930.814697499837,
+                    "count": 1002052,
+                    "self": 10.428872899525231,
+                    "children": {
+                        "env_step": {
+                            "total": 3920.385824600312,
+                            "count": 1002052,
+                            "self": 1712.4296051002211,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2202.2326369000148,
+                                    "count": 1002052,
+                                    "self": 26.523862099877533,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2175.7087748001372,
+                                            "count": 1002052,
+                                            "self": 2175.7087748001372
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 5.723582600075961,
+                                    "count": 1002052,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 3926.235519199897,
+                                            "count": 1002052,
+                                            "is_parallel": true,
+                                            "self": 2889.4922947998657,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.00024530000000000385,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.00011580000000011026,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0001294999999998936,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0001294999999998936
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1036.7429791000313,
+                                                    "count": 1002052,
+                                                    "is_parallel": true,
+                                                    "self": 55.44350770002029,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 88.42687889989358,
+                                                            "count": 1002052,
+                                                            "is_parallel": true,
+                                                            "self": 88.42687889989358
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 740.1925621001417,
+                                                            "count": 1002052,
+                                                            "is_parallel": true,
+                                                            "self": 740.1925621001417
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 152.6800303999758,
+                                                            "count": 1002052,
+                                                            "is_parallel": true,
+                                                            "self": 85.26830909995925,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 67.41172130001655,
+                                                                    "count": 2004104,
+                                                                    "is_parallel": true,
+                                                                    "self": 67.41172130001655
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.189999986512703e-05,
+                    "count": 1,
+                    "self": 2.189999986512703e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 3940.6640544999645,
+                                    "count": 116636,
+                                    "is_parallel": true,
+                                    "self": 4.5521021999365985,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 2043.5126325000251,
+                                            "count": 116636,
+                                            "is_parallel": true,
+                                            "self": 2043.075050900024,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.43758160000103885,
+                                                    "count": 16,
+                                                    "is_parallel": true,
+                                                    "self": 0.43758160000103885
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 1892.599319800003,
+                                            "count": 600,
+                                            "is_parallel": true,
+                                            "self": 570.043004099949,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1322.556315700054,
+                                                    "count": 93600,
+                                                    "is_parallel": true,
+                                                    "self": 1322.556315700054
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.027191399999992427,
+                    "count": 1,
+                    "self": 0.005660700000134966,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.02153069999985746,
+                            "count": 1,
+                            "self": 0.02153069999985746
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,71 @@
+{
+    "pattern": {
+        "lesson_num": 0
+    },
+    "task": {
+        "lesson_num": 0
+    },
+    "Agent": {
+        "checkpoints": [
+            {
+                "steps": 6498432,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-6498432.onnx",
+                "reward": null,
+                "creation_time": 1715268520.4349413,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-6498432.pt"
+                ]
+            },
+            {
+                "steps": 6999096,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-6999096.onnx",
+                "reward": 4551.414079938616,
+                "creation_time": 1715268761.849894,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-6999096.pt"
+                ]
+            },
+            {
+                "steps": 7498432,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-7498432.onnx",
+                "reward": null,
+                "creation_time": 1715269012.488705,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-7498432.pt"
+                ]
+            },
+            {
+                "steps": 7999096,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-7999096.onnx",
+                "reward": 4531.610377720424,
+                "creation_time": 1715269253.1782167,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-7999096.pt"
+                ]
+            },
+            {
+                "steps": 8016384,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-8016384.onnx",
+                "reward": null,
+                "creation_time": 1715269260.1656647,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-8016384.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 8016384,
+            "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent.onnx",
+            "reward": null,
+            "creation_time": 1715269260.1656647,
+            "auxillary_file_paths": [
+                "results\\WindFarmControl/train/WindFarmControl_pattern_6_task_0_run_id_1_train\\Agent\\Agent-8016384.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.30.0",
+        "torch_version": "1.7.1+cu110"
+    }
+}