{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6509416103363037, "min": 0.6509416103363037, "max": 1.4029514789581299, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19444.927734375, "min": 19444.927734375, "max": 42559.9375, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3457738161087036, "min": -0.2010049670934677, "max": 0.4050307869911194, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 90.24696350097656, "min": -47.63817596435547, "max": 106.92813110351562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 135.45318603515625, "min": -0.0005455068894661963, "max": 135.45318603515625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 35353.28125, "min": -0.13746774196624756, "max": 35353.28125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07116542290618998, "min": 0.06388296890197255, "max": 0.07385484702164331, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9963159206866596, "min": 0.4817108204762247, "max": 1.0532231060913582, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 1851.6963029361907, "min": 0.00024384026576801846, "max": 1851.6963029361907, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 25923.74824110667, "min": 0.0025457051088406558, "max": 25923.74824110667, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.300640423628573e-06, "min": 7.300640423628573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010220896593080002, "min": 0.00010220896593080002, "max": 0.0030219080926974003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243351428571427, "min": 0.10243351428571427, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340692, "min": 1.3886848, "max": 2.4009790000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025310807714285725, "min": 0.00025310807714285725, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035435130800000017, "min": 0.0035435130800000017, "max": 0.10075952973999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00783002283424139, "min": 0.00782970804721117, "max": 0.35662126541137695, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10962032526731491, "min": 0.10961591452360153, "max": 2.4963488578796387, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 480.453125, "min": 432.96923076923076, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30749.0, "min": 15984.0, "max": 32905.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3007280931342393, "min": -1.0000000521540642, "max": 1.5362522881764633, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 83.24659796059132, "min": -32.000001668930054, "max": 99.85639873147011, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3007280931342393, "min": -1.0000000521540642, "max": 1.5362522881764633, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 83.24659796059132, "min": -32.000001668930054, "max": 99.85639873147011, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04010859162281122, "min": 0.03515081175047761, "max": 7.064080120995641, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.566949863859918, "min": 2.2848027637810446, "max": 113.02528193593025, "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": "1710786859", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1710788925" }, "total": 2065.710465668, "count": 1, "self": 0.5936395920007271, "children": { "run_training.setup": { "total": 0.10453902899962486, "count": 1, "self": 0.10453902899962486 }, "TrainerController.start_learning": { "total": 2065.0122870469995, "count": 1, "self": 1.2720890359605619, "children": { "TrainerController._reset_env": { "total": 4.141118183000344, "count": 1, "self": 4.141118183000344 }, "TrainerController.advance": { "total": 2059.508407389039, "count": 63335, "self": 1.3779396110348898, "children": { "env_step": { "total": 1401.782214859019, "count": 63335, "self": 1273.0833209249695, "children": { "SubprocessEnvManager._take_step": { "total": 127.91015102903384, "count": 63335, "self": 4.6484490040134006, "children": { "TorchPolicy.evaluate": { "total": 123.26170202502044, "count": 62557, "self": 123.26170202502044 } } }, "workers": { "total": 0.7887429050156243, "count": 63335, "self": 0.0, "children": { "worker_root": { "total": 2060.2796150749655, "count": 63335, "is_parallel": true, "self": 896.9964837560178, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005344448999949236, "count": 1, "is_parallel": true, "self": 0.003886063999743783, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014583850002054533, "count": 8, "is_parallel": true, "self": 0.0014583850002054533 } } }, "UnityEnvironment.step": { "total": 0.05039602599981663, "count": 1, "is_parallel": true, "self": 0.000611895000020013, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004999789998691995, "count": 1, "is_parallel": true, "self": 0.0004999789998691995 }, "communicator.exchange": { "total": 0.04751114500004405, "count": 1, "is_parallel": true, "self": 0.04751114500004405 }, "steps_from_proto": { "total": 0.0017730069998833642, "count": 1, "is_parallel": true, "self": 0.00037849700083825155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013945099990451126, "count": 8, "is_parallel": true, "self": 0.0013945099990451126 } } } } } } }, "UnityEnvironment.step": { "total": 1163.2831313189477, "count": 63334, "is_parallel": true, "self": 34.29297426590665, "children": { "UnityEnvironment._generate_step_input": { "total": 24.028847002978637, "count": 63334, "is_parallel": true, "self": 24.028847002978637 }, "communicator.exchange": { "total": 998.5090422270491, "count": 63334, "is_parallel": true, "self": 998.5090422270491 }, "steps_from_proto": { "total": 106.45226782301324, "count": 63334, "is_parallel": true, "self": 20.45399349096897, "children": { "_process_rank_one_or_two_observation": { "total": 85.99827433204428, "count": 506672, "is_parallel": true, "self": 85.99827433204428 } } } } } } } } } } }, "trainer_advance": { "total": 656.348252918985, "count": 63335, "self": 2.3225651520169777, "children": { "process_trajectory": { "total": 120.01191298296544, "count": 63335, "self": 119.74777153796458, "children": { "RLTrainer._checkpoint": { "total": 0.2641414450008597, "count": 2, "self": 0.2641414450008597 } } }, "_update_policy": { "total": 534.0137747840026, "count": 436, "self": 331.4164921870338, "children": { "TorchPPOOptimizer.update": { "total": 202.59728259696885, "count": 22869, "self": 202.59728259696885 } } } } } } }, "trainer_threads": { "total": 8.899996828404255e-07, "count": 1, "self": 8.899996828404255e-07 }, "TrainerController._save_models": { "total": 0.09067154900003516, "count": 1, "self": 0.0015128670002013678, "children": { "RLTrainer._checkpoint": { "total": 0.08915868199983379, "count": 1, "self": 0.08915868199983379 } } } } } } }