{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.44589558243751526, "min": 0.42532193660736084, "max": 1.79140305519104, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 6744.61669921875, "min": 6259.1630859375, "max": 27053.76953125, "count": 200 }, "Agent.Environment.EpisodeLength.mean": { "value": 151.72727272727272, "min": 26.29281767955801, "max": 207.65217391304347, "count": 200 }, "Agent.Environment.EpisodeLength.sum": { "value": 15021.0, "min": 13128.0, "max": 16833.0, "count": 200 }, "Agent.OceanPlasticCollector.GlobalReward.mean": { "value": 286.7894780923442, "min": 1.1800377699405407, "max": 388.8985731244282, "count": 200 }, "Agent.OceanPlasticCollector.GlobalReward.sum": { "value": 53342.842925176024, "min": 623.0599425286055, "max": 65570.11977723241, "count": 200 }, "Agent.OceanPlasticCollector.LocalReward.mean": { "value": 169.48924731182797, "min": 17.577651515151516, "max": 191.92857142857142, "count": 200 }, "Agent.OceanPlasticCollector.LocalReward.sum": { "value": 31525.0, "min": 8876.0, "max": 34975.0, "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": 2999934.0, "min": 14995.0, "max": 2999934.0, "count": 200 }, "Agent.Step.sum": { "value": 2999934.0, "min": 14995.0, "max": 2999934.0, "count": 200 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.07356642931699753, "min": -0.33354872465133667, "max": 1.1176748275756836, "count": 200 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 7.356642723083496, "min": -88.1844711303711, "max": 253.16246032714844, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 371.4970397949219, "min": 3.141871690750122, "max": 406.1068115234375, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 37149.703125, "min": 1410.700439453125, "max": 58084.30859375, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 1165.9769846343995, "min": 90.62464488949237, "max": 1429.8103665571946, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 116597.69846343994, "min": 40694.93034648895, "max": 128350.83875656128, "count": 200 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.19991103200241922, "min": 0.04842318139165507, "max": 1.0922839760062206, "count": 200 }, "Agent.Policy.CuriosityReward.sum": { "value": 19.991103200241923, "min": 19.56209521740675, "max": 233.2555589172989, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 1049.3792574310303, "min": 81.56217563912958, "max": 1286.8292953830498, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 104937.92574310303, "min": 36625.43554967642, "max": 115515.75228118896, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.02173497434705496, "min": 0.015104639964799086, "max": 0.03335427862281601, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.02173497434705496, "min": 0.015104639964799086, "max": 0.057910619350150225, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 7911.067073567709, "min": 1563.9071044921875, "max": 8878.087890625, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 7911.067073567709, "min": 1563.9071044921875, "max": 16406.7236328125, "count": 200 }, "Agent.Policy.LearningRate.mean": { "value": 8.607997131000032e-07, "min": 8.607997131000032e-07, "max": 0.00029895630034790005, "count": 200 }, "Agent.Policy.LearningRate.sum": { "value": 8.607997131000032e-07, "min": 8.607997131000032e-07, "max": 0.0005927421024192999, "count": 200 }, "Agent.Policy.Epsilon.mean": { "value": 0.1002869, "min": 0.1002869, "max": 0.19965209999999994, "count": 200 }, "Agent.Policy.Epsilon.sum": { "value": 0.1002869, "min": 0.1002869, "max": 0.3975807, "count": 200 }, "Agent.Policy.Beta.mean": { "value": 2.431631000000006e-05, "min": 2.431631000000006e-05, "max": 0.004982639789999998, "count": 200 }, "Agent.Policy.Beta.sum": { "value": 2.431631000000006e-05, "min": 2.431631000000006e-05, "max": 0.00987927693, "count": 200 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.013924151131262382, "min": 0.012690329737961293, "max": 0.1835711356252432, "count": 200 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.013924151131262382, "min": 0.012690329737961293, "max": 0.24826578845580421, "count": 200 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 0.07042228939632575, "min": 0.05831307669480642, "max": 1.7913234074910482, "count": 200 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 0.07042228939632575, "min": 0.05831307669480642, "max": 3.1144038677215575, "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": "1716271201", "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/OceanPlasticCollection_task_1_run_id_0_train.yaml --run-id=OceanPlasticCollection/train/OceanPlasticCollection_task_1_run_id_0_train --base-port 5007", "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": "1716300263" }, "total": 29063.168051, "count": 1, "self": 1.468607000002521, "children": { "run_training.setup": { "total": 0.058088099999999976, "count": 1, "self": 0.058088099999999976 }, "TrainerController.start_learning": { "total": 29061.6413559, "count": 1, "self": 24.14261530045769, "children": { "TrainerController._reset_env": { "total": 4.243644199999999, "count": 1, "self": 4.243644199999999 }, "TrainerController.advance": { "total": 29033.015204899544, "count": 1007298, "self": 22.936762998244376, "children": { "env_step": { "total": 29010.0784419013, "count": 1007298, "self": 18977.19774700009, "children": { "SubprocessEnvManager._take_step": { "total": 10019.075315700178, "count": 1007298, "self": 42.5171780018718, "children": { "TorchPolicy.evaluate": { "total": 9976.558137698306, "count": 1000098, "self": 9976.558137698306 } } }, "workers": { "total": 13.805379201032467, "count": 1007298, "self": 0.0, "children": { "worker_root": { "total": 29034.415797299407, "count": 1007298, "is_parallel": true, "self": 10949.139479400816, "children": { "steps_from_proto": { "total": 0.0004306000000000587, "count": 1, "is_parallel": true, "self": 0.00011079999999985546, "children": { "_process_maybe_compressed_observation": { "total": 0.00023300000000014975, "count": 2, "is_parallel": true, "self": 3.339999999996124e-05, "children": { "_observation_to_np_array": { "total": 0.00019960000000018852, "count": 3, "is_parallel": true, "self": 0.00019960000000018852 } } }, "_process_rank_one_or_two_observation": { "total": 8.68000000000535e-05, "count": 2, "is_parallel": true, "self": 8.68000000000535e-05 } } }, "UnityEnvironment.step": { "total": 18085.27588729859, "count": 1007298, "is_parallel": true, "self": 134.34906380009124, "children": { "UnityEnvironment._generate_step_input": { "total": 65.43167780016917, "count": 1007298, "is_parallel": true, "self": 65.43167780016917 }, "communicator.exchange": { "total": 17397.16803759995, "count": 1007298, "is_parallel": true, "self": 17397.16803759995 }, "steps_from_proto": { "total": 488.3271080983802, "count": 1007298, "is_parallel": true, "self": 114.74149420003545, "children": { "_process_maybe_compressed_observation": { "total": 309.15640659773845, "count": 2014596, "is_parallel": true, "self": 40.06789069569027, "children": { "_observation_to_np_array": { "total": 269.0885159020482, "count": 3027150, "is_parallel": true, "self": 269.0885159020482 } } }, "_process_rank_one_or_two_observation": { "total": 64.42920730060631, "count": 2014596, "is_parallel": true, "self": 64.42920730060631 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.8799997380701825e-05, "count": 1, "self": 2.8799997380701825e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 29033.17883840124, "count": 1526568, "is_parallel": true, "self": 67.84328040284527, "children": { "process_trajectory": { "total": 24385.49959319836, "count": 1526568, "is_parallel": true, "self": 24383.658545898357, "children": { "RLTrainer._checkpoint": { "total": 1.8410473000030834, "count": 6, "is_parallel": true, "self": 1.8410473000030834 } } }, "_update_policy": { "total": 4579.835964800032, "count": 282, "is_parallel": true, "self": 3046.1118077001292, "children": { "TorchPPOOptimizer.update": { "total": 1533.724157099903, "count": 8532, "is_parallel": true, "self": 1533.724157099903 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2398627000002307, "count": 1, "self": 0.019564499998523388, "children": { "RLTrainer._checkpoint": { "total": 0.2202982000017073, "count": 1, "self": 0.2202982000017073 } } } } } } }