{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.8078989386558533, "min": 0.7593706846237183, "max": 1.0973856449127197, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 32322.421875, "min": 30350.52734375, "max": 43991.99609375, "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": 9.691316604614258, "min": 2.4082863330841064, "max": 9.822656631469727, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 232.5915985107422, "min": 55.39058303833008, "max": 235.74375915527344, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.05076175101509314, "min": 0.044548681806652835, "max": 0.05523217123002738, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.15228525304527943, "min": 0.10742141217148551, "max": 0.16569651369008215, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.004462618914701688, "min": 0.003462232455127551, "max": 4.057633353707692, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.013387856744105064, "min": 0.010386697365382653, "max": 8.473910281345958, "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": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.mean": { "value": 4819.977478027344, "min": 1795.089584350586, "max": 4888.54296875, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.sum": { "value": 38559.81982421875, "min": 14360.716674804688, "max": 39108.34375, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4837.719398498535, "min": 1732.9044075012207, "max": 4889.512763977051, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 38701.75518798828, "min": 13863.235260009766, "max": 39116.102111816406, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4837.719398498535, "min": 1732.9044075012207, "max": 4889.512763977051, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 38701.75518798828, "min": 13863.235260009766, "max": 39116.102111816406, "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": "1715253532", "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_1_run_id_1_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_4_task_1_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": "1715257455" }, "total": 3923.2585861000002, "count": 1, "self": 0.17206190000024435, "children": { "run_training.setup": { "total": 0.04647599999999996, "count": 1, "self": 0.04647599999999996 }, "TrainerController.start_learning": { "total": 3923.0400482, "count": 1, "self": 11.091624200025308, "children": { "TrainerController._reset_env": { "total": 1.6140717, "count": 1, "self": 1.6140717 }, "TrainerController.advance": { "total": 3910.3075827999746, "count": 1002052, "self": 10.50763850013891, "children": { "env_step": { "total": 3899.7999442998357, "count": 1002052, "self": 1664.9441964998846, "children": { "SubprocessEnvManager._take_step": { "total": 2228.02891719985, "count": 1002052, "self": 28.391092299971206, "children": { "TorchPolicy.evaluate": { "total": 2199.637824899879, "count": 1002052, "self": 2199.637824899879 } } }, "workers": { "total": 6.826830600101098, "count": 1002052, "self": 0.0, "children": { "worker_root": { "total": 3907.741042400028, "count": 1002052, "is_parallel": true, "self": 2927.620541799868, "children": { "steps_from_proto": { "total": 0.00024360000000001047, "count": 1, "is_parallel": true, "self": 0.00011280000000002399, "children": { "_process_rank_one_or_two_observation": { "total": 0.00013079999999998648, "count": 2, "is_parallel": true, "self": 0.00013079999999998648 } } }, "UnityEnvironment.step": { "total": 980.1202570001601, "count": 1002052, "is_parallel": true, "self": 52.367642900181295, "children": { "UnityEnvironment._generate_step_input": { "total": 87.25601739988949, "count": 1002052, "is_parallel": true, "self": 87.25601739988949 }, "communicator.exchange": { "total": 695.5269677000049, "count": 1002052, "is_parallel": true, "self": 695.5269677000049 }, "steps_from_proto": { "total": 144.9696290000844, "count": 1002052, "is_parallel": true, "self": 81.6377007002381, "children": { "_process_rank_one_or_two_observation": { "total": 63.33192829984631, "count": 2004104, "is_parallel": true, "self": 63.33192829984631 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.3999999939405825e-05, "count": 1, "self": 2.3999999939405825e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3920.4726630000646, "count": 110417, "is_parallel": true, "self": 4.6946627000661465, "children": { "process_trajectory": { "total": 1947.5996649000017, "count": 110417, "is_parallel": true, "self": 1947.148173000002, "children": { "RLTrainer._checkpoint": { "total": 0.4514918999995814, "count": 16, "is_parallel": true, "self": 0.4514918999995814 } } }, "_update_policy": { "total": 1968.1783353999967, "count": 600, "is_parallel": true, "self": 579.7142480999787, "children": { "TorchPPOOptimizer.update": { "total": 1388.464087300018, "count": 93600, "is_parallel": true, "self": 1388.464087300018 } } } } } } } } }, "TrainerController._save_models": { "total": 0.026745500000288303, "count": 1, "self": 0.005441800000426156, "children": { "RLTrainer._checkpoint": { "total": 0.021303699999862147, "count": 1, "self": 0.021303699999862147 } } } } } } }