{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.7487905025482178, "min": 0.5864184498786926, "max": 1.0954581499099731, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 29963.599609375, "min": 23452.046875, "max": 43888.4375, "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": 9.750008583068848, "min": 2.483990430831909, "max": 9.794022560119629, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 234.00021362304688, "min": 57.131778717041016, "max": 235.05654907226562, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.05110003270746102, "min": 0.04344587100497429, "max": 0.05577823658319494, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.15330009812238304, "min": 0.09584244352057189, "max": 0.1673347097495848, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.0048299082340928995, "min": 0.0035734779088208656, "max": 4.954870798625052, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.0144897247022787, "min": 0.010720433726462596, "max": 9.909741597250104, "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": 4855.470642089844, "min": 1496.6440200805664, "max": 4889.613586425781, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.sum": { "value": 38843.76513671875, "min": 11973.152160644531, "max": 39116.90869140625, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4851.871337890625, "min": 1742.0011529922485, "max": 4893.7439041137695, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 38814.970703125, "min": 13936.009223937988, "max": 39149.951232910156, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4851.871337890625, "min": 1742.0011529922485, "max": 4893.7439041137695, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 38814.970703125, "min": 13936.009223937988, "max": 39149.951232910156, "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": "1716310229", "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_8_task_1_run_id_2_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_8_task_1_run_id_2_train --base-port 5009", "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": "1716315736" }, "total": 5507.6809619000005, "count": 1, "self": 0.20196660000056, "children": { "run_training.setup": { "total": 0.061003200000000035, "count": 1, "self": 0.061003200000000035 }, "TrainerController.start_learning": { "total": 5507.4179920999995, "count": 1, "self": 18.071718999837685, "children": { "TrainerController._reset_env": { "total": 3.8922267999999995, "count": 1, "self": 3.8922267999999995 }, "TrainerController.advance": { "total": 5485.418861400161, "count": 1002050, "self": 15.549165599899425, "children": { "env_step": { "total": 5469.869695800262, "count": 1002050, "self": 2110.8445559002266, "children": { "SubprocessEnvManager._take_step": { "total": 3350.797693199916, "count": 1002050, "self": 35.539810699322516, "children": { "TorchPolicy.evaluate": { "total": 3315.2578825005935, "count": 1002050, "self": 3315.2578825005935 } } }, "workers": { "total": 8.227446700119302, "count": 1002050, "self": 0.0, "children": { "worker_root": { "total": 5485.25349300001, "count": 1002050, "is_parallel": true, "self": 4229.318325200127, "children": { "steps_from_proto": { "total": 0.00026780000000004023, "count": 1, "is_parallel": true, "self": 0.0001335000000000086, "children": { "_process_rank_one_or_two_observation": { "total": 0.00013430000000003162, "count": 2, "is_parallel": true, "self": 0.00013430000000003162 } } }, "UnityEnvironment.step": { "total": 1255.934899999883, "count": 1002050, "is_parallel": true, "self": 58.66727299893978, "children": { "UnityEnvironment._generate_step_input": { "total": 78.03818370012502, "count": 1002050, "is_parallel": true, "self": 78.03818370012502 }, "communicator.exchange": { "total": 952.499582400736, "count": 1002050, "is_parallel": true, "self": 952.499582400736 }, "steps_from_proto": { "total": 166.72986090008226, "count": 1002050, "is_parallel": true, "self": 89.93004990013088, "children": { "_process_rank_one_or_two_observation": { "total": 76.79981099995138, "count": 2004100, "is_parallel": true, "self": 76.79981099995138 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.240000023652101e-05, "count": 1, "self": 3.240000023652101e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 5501.4550517000525, "count": 174875, "is_parallel": true, "self": 9.243340100028945, "children": { "process_trajectory": { "total": 2972.4364139000236, "count": 174875, "is_parallel": true, "self": 2971.8741748000252, "children": { "RLTrainer._checkpoint": { "total": 0.5622390999982372, "count": 16, "is_parallel": true, "self": 0.5622390999982372 } } }, "_update_policy": { "total": 2519.7752977, "count": 600, "is_parallel": true, "self": 741.8472785000695, "children": { "TorchPPOOptimizer.update": { "total": 1777.9280191999305, "count": 93600, "is_parallel": true, "self": 1777.9280191999305 } } } } } } } } }, "TrainerController._save_models": { "total": 0.03515250000054948, "count": 1, "self": 0.006966900000406895, "children": { "RLTrainer._checkpoint": { "total": 0.028185600000142585, "count": 1, "self": 0.028185600000142585 } } } } } } }