{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6858499050140381, "min": 0.6795541644096375, "max": 1.5101670026779175, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20553.55078125, "min": 20332.259765625, "max": 45812.42578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.21509145200252533, "min": -0.10638869553804398, "max": 0.21509145200252533, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 54.41813659667969, "min": -25.63967514038086, "max": 54.45438766479492, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01463516429066658, "min": 0.008874990977346897, "max": 0.19007067382335663, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.7026965618133545, "min": 2.245372772216797, "max": 45.61696243286133, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06663858966704776, "min": 0.0647611138524999, "max": 0.07452051978998854, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9329402553386686, "min": 0.502644263280672, "max": 1.1178077968498281, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011138677575844736, "min": 0.00013485382591629585, "max": 0.012187402453970762, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1559414860618263, "min": 0.0016182459109955502, "max": 0.17062363435559066, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.41086895831429e-06, "min": 7.41086895831429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010375216541640005, "min": 0.00010375216541640005, "max": 0.0030070033976656, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247025714285715, "min": 0.10247025714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345836, "min": 1.3691136000000002, "max": 2.3591663000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002567786885714287, "min": 0.0002567786885714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003594901640000002, "min": 0.003594901640000002, "max": 0.10025320655999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011575514450669289, "min": 0.011575514450669289, "max": 0.2591188848018646, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16205720603466034, "min": 0.16205720603466034, "max": 1.8138322830200195, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 644.3191489361702, "min": 599.9038461538462, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30283.0, "min": 15984.0, "max": 32558.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8448637958536757, "min": -1.0000000521540642, "max": 1.0538384239547527, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 39.70859840512276, "min": -32.000001668930054, "max": 54.799598045647144, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8448637958536757, "min": -1.0000000521540642, "max": 1.0538384239547527, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 39.70859840512276, "min": -32.000001668930054, "max": 54.799598045647144, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07704595548838893, "min": 0.07639921394002158, "max": 5.099954700097442, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6211599079542793, "min": 3.6211599079542793, "max": 81.59927520155907, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680790561", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680792621" }, "total": 2060.1478468600003, "count": 1, "self": 0.48805707600013193, "children": { "run_training.setup": { "total": 0.10672441300016544, "count": 1, "self": 0.10672441300016544 }, "TrainerController.start_learning": { "total": 2059.553065371, "count": 1, "self": 1.3792012260000774, "children": { "TrainerController._reset_env": { "total": 3.668850022000015, "count": 1, "self": 3.668850022000015 }, "TrainerController.advance": { "total": 2054.4062615089997, "count": 63282, "self": 1.50842975705973, "children": { "env_step": { "total": 1439.6126021220257, "count": 63282, "self": 1330.4988628558945, "children": { "SubprocessEnvManager._take_step": { "total": 108.23864930104833, "count": 63282, "self": 4.889577669086066, "children": { "TorchPolicy.evaluate": { "total": 103.34907163196226, "count": 62565, "self": 103.34907163196226 } } }, "workers": { "total": 0.8750899650829069, "count": 63282, "self": 0.0, "children": { "worker_root": { "total": 2054.4030669040376, "count": 63282, "is_parallel": true, "self": 838.0295059980972, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018173809999098012, "count": 1, "is_parallel": true, "self": 0.0005687570003374276, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012486239995723736, "count": 8, "is_parallel": true, "self": 0.0012486239995723736 } } }, "UnityEnvironment.step": { "total": 0.04849578699986523, "count": 1, "is_parallel": true, "self": 0.0007032960004380584, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004895979998309485, "count": 1, "is_parallel": true, "self": 0.0004895979998309485 }, "communicator.exchange": { "total": 0.04564058399978421, "count": 1, "is_parallel": true, "self": 0.04564058399978421 }, "steps_from_proto": { "total": 0.0016623089998120122, "count": 1, "is_parallel": true, "self": 0.0003793639998548315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012829449999571807, "count": 8, "is_parallel": true, "self": 0.0012829449999571807 } } } } } } }, "UnityEnvironment.step": { "total": 1216.3735609059404, "count": 63281, "is_parallel": true, "self": 32.49111484591231, "children": { "UnityEnvironment._generate_step_input": { "total": 24.400407521019815, "count": 63281, "is_parallel": true, "self": 24.400407521019815 }, "communicator.exchange": { "total": 1061.9296520679643, "count": 63281, "is_parallel": true, "self": 1061.9296520679643 }, "steps_from_proto": { "total": 97.55238647104397, "count": 63281, "is_parallel": true, "self": 20.903509349959222, "children": { "_process_rank_one_or_two_observation": { "total": 76.64887712108475, "count": 506248, "is_parallel": true, "self": 76.64887712108475 } } } } } } } } } } }, "trainer_advance": { "total": 613.2852296299143, "count": 63282, "self": 2.385895598895104, "children": { "process_trajectory": { "total": 108.51027713801909, "count": 63282, "self": 108.28821818601887, "children": { "RLTrainer._checkpoint": { "total": 0.22205895200022496, "count": 2, "self": 0.22205895200022496 } } }, "_update_policy": { "total": 502.3890568930001, "count": 432, "self": 323.75208102396164, "children": { "TorchPPOOptimizer.update": { "total": 178.63697586903845, "count": 22806, "self": 178.63697586903845 } } } } } } }, "trainer_threads": { "total": 1.0530002327868715e-06, "count": 1, "self": 1.0530002327868715e-06 }, "TrainerController._save_models": { "total": 0.09875156099997184, "count": 1, "self": 0.0015701499996794155, "children": { "RLTrainer._checkpoint": { "total": 0.09718141100029243, "count": 1, "self": 0.09718141100029243 } } } } } } }