{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 1.0342463254928589, "min": 0.8567436933517456, "max": 1.0977368354797363, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 41378.12890625, "min": 34276.6015625, "max": 43979.73046875, "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": 9.325874328613281, "min": 0.7655065655708313, "max": 9.509753227233887, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 223.82098388671875, "min": 18.37215805053711, "max": 228.23406982421875, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.04881577084447527, "min": 0.04492947267089409, "max": 0.05480822551688771, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.1464473125334258, "min": 0.09814778697909787, "max": 0.16442467655066312, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.29578603130103726, "min": 0.0682248831814384, "max": 1.462727802572772, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.8873580939031117, "min": 0.20467464954431522, "max": 2.925455605145544, "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": 4625.7371826171875, "min": 618.1424263715744, "max": 4678.6807861328125, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.sum": { "value": 37005.8974609375, "min": 4945.139410972595, "max": 37429.4462890625, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4625.749465942383, "min": 802.4631873253398, "max": 4682.931671142578, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 37005.99572753906, "min": 6419.705498602719, "max": 37463.453369140625, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4625.749465942383, "min": 802.4631873253398, "max": 4682.931671142578, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 37005.99572753906, "min": 6419.705498602719, "max": 37463.453369140625, "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": "1716278148", "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_0_run_id_0_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_8_task_0_run_id_0_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": "1716285124" }, "total": 6975.7818057, "count": 1, "self": 0.34803290000036213, "children": { "run_training.setup": { "total": 0.06823010000000007, "count": 1, "self": 0.06823010000000007 }, "TrainerController.start_learning": { "total": 6975.3655427, "count": 1, "self": 21.392211200079146, "children": { "TrainerController._reset_env": { "total": 4.3076970999999995, "count": 1, "self": 4.3076970999999995 }, "TrainerController.advance": { "total": 6949.629124099921, "count": 1002051, "self": 19.631331999895338, "children": { "env_step": { "total": 6929.997792100025, "count": 1002051, "self": 2292.9432863998, "children": { "SubprocessEnvManager._take_step": { "total": 4627.3965150002705, "count": 1002051, "self": 38.25333070077522, "children": { "TorchPolicy.evaluate": { "total": 4589.143184299495, "count": 1002051, "self": 4589.143184299495 } } }, "workers": { "total": 9.657990699955352, "count": 1002051, "self": 0.0, "children": { "worker_root": { "total": 6951.450070599854, "count": 1002051, "is_parallel": true, "self": 5560.053164699688, "children": { "steps_from_proto": { "total": 0.00048599999999998644, "count": 1, "is_parallel": true, "self": 0.00033770000000066247, "children": { "_process_rank_one_or_two_observation": { "total": 0.00014829999999932397, "count": 2, "is_parallel": true, "self": 0.00014829999999932397 } } }, "UnityEnvironment.step": { "total": 1391.3964199001666, "count": 1002051, "is_parallel": true, "self": 66.13279789980515, "children": { "UnityEnvironment._generate_step_input": { "total": 96.4390646001216, "count": 1002051, "is_parallel": true, "self": 96.4390646001216 }, "communicator.exchange": { "total": 1037.158965500481, "count": 1002051, "is_parallel": true, "self": 1037.158965500481 }, "steps_from_proto": { "total": 191.66559189975908, "count": 1002051, "is_parallel": true, "self": 105.45197919906975, "children": { "_process_rank_one_or_two_observation": { "total": 86.21361270068932, "count": 2004102, "is_parallel": true, "self": 86.21361270068932 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.200000057608122e-05, "count": 1, "self": 4.200000057608122e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 6968.055332399885, "count": 224650, "is_parallel": true, "self": 11.720379300204513, "children": { "process_trajectory": { "total": 3783.882188399685, "count": 224650, "is_parallel": true, "self": 3783.2448023996863, "children": { "RLTrainer._checkpoint": { "total": 0.6373859999991396, "count": 16, "is_parallel": true, "self": 0.6373859999991396 } } }, "_update_policy": { "total": 3172.4527646999954, "count": 600, "is_parallel": true, "self": 828.331355099876, "children": { "TorchPPOOptimizer.update": { "total": 2344.1214096001195, "count": 93600, "is_parallel": true, "self": 2344.1214096001195 } } } } } } } } }, "TrainerController._save_models": { "total": 0.03646829999979673, "count": 1, "self": 0.004892799999652198, "children": { "RLTrainer._checkpoint": { "total": 0.03157550000014453, "count": 1, "self": 0.03157550000014453 } } } } } } }