Upload 17 files

Agent.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ef0a1d53f2e1d844e1b6b7f4f3c3cf67e3513ce515b45baa04064c80e25a73
+size 21336

Agent/Agent-6498432.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2d12591e1d7740ab8b895693c1bf707d4fd7b594275f145a7c72fc2258fca7
+size 21336

Agent/Agent-6498432.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea40ca6766bc4e81a38d63b1dc79cbfebfbe2e8c50f65bc2becc143d41e85d9f
+size 129607

Agent/Agent-6999096.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec7f0d3ab6269d2b6bcde9c270869194eb83112dfcaffdef51bf06f5694819c
+size 21336

Agent/Agent-6999096.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9bc3062bb533d58beebd668ee302b3d1141f9e9e5a45c3e52310d8cf9d98d3c
+size 129607

Agent/Agent-7498432.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c57b92f0ca99f979c98eb712f0515bfadff09cd5d011e2f9045715011246c9
+size 21336

Agent/Agent-7498432.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2432b3bff68aa648d7fab43f0138431d403635c3003be438e5a975b8455e5d8
+size 129607

Agent/Agent-7999096.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f4a7ea1f1d27889741d08ef4d82f627971267f12ab34cac8049657ba627b5f
+size 21336

Agent/Agent-7999096.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c689d16117e1fa707a2004a674e0b34c3c1014da9952735346f30bbb7e5c35f
+size 129607

Agent/Agent-8016384.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ef0a1d53f2e1d844e1b6b7f4f3c3cf67e3513ce515b45baa04064c80e25a73
+size 21336

Agent/Agent-8016384.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b475ad1b24b7a6c151a0c8134df3188a24721e1d80c30904f0a86fee81e9e3
+size 129607

Agent/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b475ad1b24b7a6c151a0c8134df3188a24721e1d80c30904f0a86fee81e9e3
+size 129607

Agent/events.out.tfevents.1715296970.RICHARD.31828.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517c54e0b8efacb259532284a08502d64c09c04af04466a6130cf3fc9932330f
+size 220208

README.md

@@ -0,0 +1,29 @@
+---
+library_name: hivex
+original_train_name: WindFarmControl_pattern_1_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-1
+  results:
+  - task:
+      type: main-task
+      name: main_task
+      task-id: 0
+      pattern-id: 1
+    dataset:
+      name: hivex-wind-farm-control
+      type: hivex-wind-farm-control
+    metrics:
+    - type: cumulative_reward
+      value: 4605.909252929688 +/- 44.381907489150954
+      name: Cumulative Reward
+      verified: true
+    - type: individual_performance
+      value: 4605.857661132813 +/- 44.379602309414665
+      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: 1
+      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_1_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": 0.9693195223808289,
+            "min": 0.8725169897079468,
+            "max": 1.096185326576233,
+            "count": 200
+        },
+        "Agent.Policy.Entropy.sum": {
+            "value": 38780.53515625,
+            "min": 34900.6796875,
+            "max": 43917.5703125,
+            "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": 9.220352172851562,
+            "min": 0.7362647652626038,
+            "max": 9.652824401855469,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 221.2884521484375,
+            "min": 16.93408966064453,
+            "max": 231.66778564453125,
+            "count": 200
+        },
+        "Agent.Losses.PolicyLoss.mean": {
+            "value": 0.050932974578043085,
+            "min": 0.04541736845428767,
+            "max": 0.05408771253929617,
+            "count": 200
+        },
+        "Agent.Losses.PolicyLoss.sum": {
+            "value": 0.15279892373412926,
+            "min": 0.10118036730758226,
+            "max": 0.16226313761788852,
+            "count": 200
+        },
+        "Agent.Losses.ValueLoss.mean": {
+            "value": 0.26359349268022925,
+            "min": 0.07681267107776847,
+            "max": 1.5398976742678012,
+            "count": 200
+        },
+        "Agent.Losses.ValueLoss.sum": {
+            "value": 0.7907804780406877,
+            "min": 0.2304380132333054,
+            "max": 3.0797953485356024,
+            "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": 4598.094543457031,
+            "min": 677.6656951904297,
+            "max": 4680.65234375,
+            "count": 200
+        },
+        "Agent.WindFarmControl.IndividualPerformance.sum": {
+            "value": 36784.75634765625,
+            "min": 5421.3255615234375,
+            "max": 37445.21875,
+            "count": 200
+        },
+        "Agent.Environment.CumulativeReward.mean": {
+            "value": 4589.000862121582,
+            "min": 812.7594861710642,
+            "max": 4672.007499694824,
+            "count": 200
+        },
+        "Agent.Environment.CumulativeReward.sum": {
+            "value": 36712.006896972656,
+            "min": 5689.316403197449,
+            "max": 37376.059997558594,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicReward.mean": {
+            "value": 4589.000862121582,
+            "min": 812.7594861710642,
+            "max": 4672.007499694824,
+            "count": 200
+        },
+        "Agent.Policy.ExtrinsicReward.sum": {
+            "value": 36712.006896972656,
+            "min": 5689.316403197449,
+            "max": 37376.059997558594,
+            "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": "1715296969",
+        "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_1_task_0_run_id_2_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_1_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": "1715301026"
+    },
+    "total": 4056.8964678,
+    "count": 1,
+    "self": 0.17192660000000615,
+    "children": {
+        "run_training.setup": {
+            "total": 0.04466569999999992,
+            "count": 1,
+            "self": 0.04466569999999992
+        },
+        "TrainerController.start_learning": {
+            "total": 4056.6798755,
+            "count": 1,
+            "self": 10.97135339987608,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.6216655,
+                    "count": 1,
+                    "self": 1.6216655
+                },
+                "TrainerController.advance": {
+                    "total": 4044.060071300124,
+                    "count": 1002052,
+                    "self": 10.519032100225104,
+                    "children": {
+                        "env_step": {
+                            "total": 4033.541039199899,
+                            "count": 1002052,
+                            "self": 1734.076014399936,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2292.744347500026,
+                                    "count": 1002052,
+                                    "self": 28.70002339987286,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2264.044324100153,
+                                            "count": 1002052,
+                                            "self": 2264.044324100153
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 6.7206772999368365,
+                                    "count": 1002052,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4040.282729500292,
+                                            "count": 1002052,
+                                            "is_parallel": true,
+                                            "self": 2998.1602124003502,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.00023560000000000247,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.00010840000000000849,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.00012719999999999398,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.00012719999999999398
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1042.1222814999417,
+                                                    "count": 1002052,
+                                                    "is_parallel": true,
+                                                    "self": 56.464939899808314,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 88.16600829991964,
+                                                            "count": 1002052,
+                                                            "is_parallel": true,
+                                                            "self": 88.16600829991964
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 744.9898393003259,
+                                                            "count": 1002052,
+                                                            "is_parallel": true,
+                                                            "self": 744.9898393003259
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 152.50149399988783,
+                                                            "count": 1002052,
+                                                            "is_parallel": true,
+                                                            "self": 84.50276190024293,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 67.9987320996449,
+                                                                    "count": 2004104,
+                                                                    "is_parallel": true,
+                                                                    "self": 67.9987320996449
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.1500000002561137e-05,
+                    "count": 1,
+                    "self": 2.1500000002561137e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 4054.015990000022,
+                                    "count": 117202,
+                                    "is_parallel": true,
+                                    "self": 4.907091600018248,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 2055.3753070999974,
+                                            "count": 117202,
+                                            "is_parallel": true,
+                                            "self": 2054.918259399998,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.4570476999994355,
+                                                    "count": 16,
+                                                    "is_parallel": true,
+                                                    "self": 0.4570476999994355
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 1993.7335913000065,
+                                            "count": 600,
+                                            "is_parallel": true,
+                                            "self": 580.5358803999904,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1413.197710900016,
+                                                    "count": 93600,
+                                                    "is_parallel": true,
+                                                    "self": 1413.197710900016
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.026763800000026094,
+                    "count": 1,
+                    "self": 0.00572150000016336,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.021042299999862735,
+                            "count": 1,
+                            "self": 0.021042299999862735
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

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_1_task_0_run_id_2_train\\Agent\\Agent-6498432.onnx",
+                "reward": null,
+                "creation_time": 1715300264.3412673,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent\\Agent-6498432.pt"
+                ]
+            },
+            {
+                "steps": 6999096,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent\\Agent-6999096.onnx",
+                "reward": 4593.847839355469,
+                "creation_time": 1715300512.976887,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent\\Agent-6999096.pt"
+                ]
+            },
+            {
+                "steps": 7498432,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent\\Agent-7498432.onnx",
+                "reward": null,
+                "creation_time": 1715300770.5704155,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent\\Agent-7498432.pt"
+                ]
+            },
+            {
+                "steps": 7999096,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent\\Agent-7999096.onnx",
+                "reward": 4597.071751185826,
+                "creation_time": 1715301018.9108918,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent\\Agent-7999096.pt"
+                ]
+            },
+            {
+                "steps": 8016384,
+                "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent\\Agent-8016384.onnx",
+                "reward": null,
+                "creation_time": 1715301026.0239363,
+                "auxillary_file_paths": [
+                    "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent\\Agent-8016384.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 8016384,
+            "file_path": "results\\WindFarmControl/train/WindFarmControl_pattern_1_task_0_run_id_2_train\\Agent.onnx",
+            "reward": null,
+            "creation_time": 1715301026.0239363,
+            "auxillary_file_paths": [
+                "results\\WindFarmControl/train/WindFarmControl_pattern_1_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"
+    }
+}