Upload 17 files

Agent.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47110265e6b97c1c7837b6ff8291a76b02d9a0a2b04adc6075d21cc38b028361
+size 21336

Agent/Agent-6498432.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271c21d7b67f4d0ec952dcd9f8a33bf58e9f37d6d30c416918efc4154a906465
+size 21336

Agent/Agent-6498432.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:361977aebd8aab4940d040b3d80d6e08908981eb727186db3070ae79be5d9c5b
+size 129607

Agent/Agent-6999096.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325cbc55760f6f5f823ff9e5605618b5185319baa028feb0b71c6c1afa190985
+size 21336

Agent/Agent-6999096.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5d2188a7922bf0186249eb4971aefb68d0ac1f786e05246abea085cfdcce22
+size 129607

Agent/Agent-7498432.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c873d3eda280bf4ea4018aed03aadd8f593ec2e2692febafb965cd727d408b4f
+size 21336

Agent/Agent-7498432.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09300f459268d8e98e5feacc209f30b278e0f4d136bac49648cc3852ceed133
+size 129607

Agent/Agent-7999096.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe69fdae12e8f719367271472d8ef50fe0b548a9b3884886e1e25c7f1d430f0
+size 21336

Agent/Agent-7999096.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ff5f6aca935e40cf4a1f86f6103b14d2248f5e25be50f8aa57f96a10d30f84
+size 129607

Agent/Agent-8016384.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47110265e6b97c1c7837b6ff8291a76b02d9a0a2b04adc6075d21cc38b028361
+size 21336

Agent/Agent-8016384.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c77666dbe076f0233fc4a1faffe66e1585bf3f1b9dff45ac01e4b878d68432a
+size 129607

Agent/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c77666dbe076f0233fc4a1faffe66e1585bf3f1b9dff45ac01e4b878d68432a
+size 129607

Agent/events.out.tfevents.1715321161.RICHARD.34620.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1d9458128d11bba38fa3759603aaeacc3b1279653e33954ad74f459ae28059
+size 224216

README.md

@@ -0,0 +1,29 @@
+---
+library_name: hivex
+original_train_name: WindFarmControl_pattern_4_task_0_run_id_2_train
+tags:
+- hivex
+- hivex-wind-farm-control
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-WFC-PPO-baseline-task-0-pattern-4
+  results:
+  - task:
+      type: main-task
+      name: main_task
+      task-id: 0
+      pattern-id: 4
+    dataset:
+      name: hivex-wind-farm-control
+      type: hivex-wind-farm-control
+    metrics:
+    - type: cumulative_reward
+      value: 4613.436940917969 +/- 38.26933135242948
+      name: Cumulative Reward
+      verified: true
+    - type: individual_performance
+      value: 4613.370803222656 +/- 38.736289986043545
+      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: 4
+      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_4_task_0_run_id_2_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": 1.0411146879196167,
+            "min": 0.8897978663444519,
+            "max": 1.0955674648284912,
+            "count": 200
+        },
+        "Agent.Policy.Entropy.sum": {
+            "value": 41644.5859375,
+            "min": 35591.9140625,
+            "max": 43866.5234375,
+            "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": 9.216448783874512,
+            "min": 0.3187240660190582,
+            "max": 9.533919334411621,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 221.1947784423828,
+            "min": 7.649377822875977,
+            "max": 228.81405639648438,
+            "count": 200
+        },
+        "Agent.Losses.PolicyLoss.mean": {
+            "value": 0.04835934573987735,
+            "min": 0.044899650071913905,
+            "max": 0.05528877122479672,
+            "count": 200
+        },
+        "Agent.Losses.PolicyLoss.sum": {
+            "value": 0.14507803721963206,
+            "min": 0.1028348121617455,
+            "max": 0.16586631367439017,
+            "count": 200
+        },
+        "Agent.Losses.ValueLoss.mean": {
+            "value": 0.2553932647362152,
+            "min": 0.08848272813373202,
+            "max": 1.3383621831114094,
+            "count": 200
+        },
+        "Agent.Losses.ValueLoss.sum": {
+            "value": 0.7661797942086456,
+            "min": 0.26544818440119605,
+            "max": 2.676724366222819,
+            "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": 4560.075744628906,
+            "min": 264.98859548568726,
+            "max": 4703.660583496094,
+            "count": 200
+        },
+        "Agent.WindFarmControl.IndividualPerformance.sum": {
+            "value": 36480.60595703125,
+            "min": 2119.908763885498,
+            "max": 37629.28466796875,
+            "count": 200
+        },
+        "Agent.Environment.CumulativeReward.mean": {
+            "value": 4555.581016540527,
+            "min": 270.6974517374753,
+            "max": 4678.846115112305,
+            "count": 200
+        },
+        "Agent.Environment.CumulativeReward.sum": {
+            "value": 36444.64813232422,
+            "min": 2165.5796138998026,
+            "max": 37430.76892089844,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicReward.mean": {
+            "value": 4555.581016540527,
+            "min": 270.6974517374753,
+            "max": 4678.846115112305,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicReward.sum": {
+            "value": 36444.64813232422,
+            "min": 2165.5796138998026,
+            "max": 37430.76892089844,
+            "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": "1715321159",
+        "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_4_task_0_run_id_2_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_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": "1715324775"
+    },
+    "total": 3615.85765,
+    "count": 1,
+    "self": 0.14807340000015756,
+    "children": {
+        "run_training.setup": {
+            "total": 0.04615530000000001,
+            "count": 1,
+            "self": 0.04615530000000001
+        },
+        "TrainerController.start_learning": {
+            "total": 3615.6634212999998,
+            "count": 1,
+            "self": 10.051278000053571,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.8622021,
+                    "count": 1,
+                    "self": 2.8622021
+                },
+                "TrainerController.advance": {
+                    "total": 3602.724098799946,
+                    "count": 1002050,
+                    "self": 9.675212799854762,
+                    "children": {
+                        "env_step": {
+                            "total": 3593.0488860000914,
+                            "count": 1002050,
+                            "self": 1634.1075297999257,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1953.6686789001872,
+                                    "count": 1002050,
+                                    "self": 25.19033400019339,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1928.4783448999938,
+                                            "count": 1002050,
+                                            "self": 1928.4783448999938
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 5.272677299978633,
+                                    "count": 1002050,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 3597.401679599778,
+                                            "count": 1002050,
+                                            "is_parallel": true,
+                                            "self": 2629.832989799741,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.00024040000000002948,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.00011179999999999524,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.00012860000000003424,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.00012860000000003424
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 967.5684494000373,
+                                                    "count": 1002050,
+                                                    "is_parallel": true,
+                                                    "self": 45.95579939999277,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 63.92699119974378,
+                                                            "count": 1002050,
+                                                            "is_parallel": true,
+                                                            "self": 63.92699119974378
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 734.384588600184,
+                                                            "count": 1002050,
+                                                            "is_parallel": true,
+                                                            "self": 734.384588600184
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 123.30107020011667,
+                                                            "count": 1002050,
+                                                            "is_parallel": true,
+                                                            "self": 68.05727880013004,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 55.243791399986634,
+                                                                    "count": 2004100,
+                                                                    "is_parallel": true,
+                                                                    "self": 55.243791399986634
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.499999982319423e-05,
+                    "count": 1,
+                    "self": 2.499999982319423e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 3611.9609419999456,
+                                    "count": 117825,
+                                    "is_parallel": true,
+                                    "self": 4.313278599895966,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 2026.9295145000467,
+                                            "count": 117825,
+                                            "is_parallel": true,
+                                            "self": 2026.5375685000463,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.39194600000041646,
+                                                    "count": 16,
+                                                    "is_parallel": true,
+                                                    "self": 0.39194600000041646
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 1580.718148900003,
+                                            "count": 600,
+                                            "is_parallel": true,
+                                            "self": 569.663019399938,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1011.0551295000649,
+                                                    "count": 93600,
+                                                    "is_parallel": true,
+                                                    "self": 1011.0551295000649
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.02581740000005084,
+                    "count": 1,
+                    "self": 0.005632200000036391,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.020185200000014447,
+                            "count": 1,
+                            "self": 0.020185200000014447
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

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_4_task_0_run_id_2_train\\Agent\\Agent-6498432.onnx",
+                "reward": null,
+                "creation_time": 1715324097.1589324,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-6498432.pt"
+                ]
+            },
+            {
+                "steps": 6999096,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-6999096.onnx",
+                "reward": 4594.123160226004,
+                "creation_time": 1715324318.0825624,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-6999096.pt"
+                ]
+            },
+            {
+                "steps": 7498432,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-7498432.onnx",
+                "reward": null,
+                "creation_time": 1715324547.8600914,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-7498432.pt"
+                ]
+            },
+            {
+                "steps": 7999096,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-7999096.onnx",
+                "reward": 4552.095912388393,
+                "creation_time": 1715324768.5004609,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-7999096.pt"
+                ]
+            },
+            {
+                "steps": 8016384,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-8016384.onnx",
+                "reward": null,
+                "creation_time": 1715324774.9240112,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-8016384.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 8016384,
+            "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent.onnx",
+            "reward": null,
+            "creation_time": 1715324774.9240112,
+            "auxillary_file_paths": [
+                "results\\WindFarmControl/train/WindFarmControl_pattern_4_task_0_run_id_2_train\\Agent\\Agent-8016384.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.30.0",
+        "torch_version": "1.7.1+cu110"
+    }
+}