{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37851184606552124, "min": 0.3752221465110779, "max": 1.5031319856643677, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11379.580078125, "min": 11124.5859375, "max": 45599.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5378025770187378, "min": -0.2273787558078766, "max": 0.5378025770187378, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.35791015625, "min": -53.888763427734375, "max": 147.35791015625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007671942003071308, "min": -0.04471804201602936, "max": 0.3118646442890167, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.102112054824829, "min": -12.163307189941406, "max": 73.91191864013672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06823058169434912, "min": 0.06386201131923953, "max": 0.07402533408533975, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9552281437208877, "min": 0.4955372136406033, "max": 1.0507477650392627, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015349060517716376, "min": 0.0001241916693842741, "max": 0.01604114818716577, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21488684724802926, "min": 0.0016144917019955633, "max": 0.22457607462032078, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.626911743442854e-06, "min": 7.626911743442854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010677676440819996, "min": 0.00010677676440819996, "max": 0.003375774774741799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254227142857142, "min": 0.10254227142857142, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355917999999999, "min": 1.3886848, "max": 2.4252582, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002639729157142856, "min": 0.0002639729157142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036956208199999986, "min": 0.0036956208199999986, "max": 0.11254329418, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007933268323540688, "min": 0.007933268323540688, "max": 0.34015053510665894, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11106576025485992, "min": 0.11106576025485992, "max": 2.3810536861419678, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 353.35714285714283, "min": 350.94117647058823, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29682.0, "min": 15984.0, "max": 32339.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5990142612939788, "min": -1.0000000521540642, "max": 1.5990142612939788, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.31719794869423, "min": -31.998801693320274, "max": 134.31719794869423, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5990142612939788, "min": -1.0000000521540642, "max": 1.5990142612939788, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.31719794869423, "min": -31.998801693320274, "max": 134.31719794869423, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028750281483336863, "min": 0.028750281483336863, "max": 7.313518545590341, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4150236446002964, "min": 2.4150236446002964, "max": 117.01629672944546, "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": "1689822176", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1689824363" }, "total": 2186.711004625, "count": 1, "self": 0.48269131200004267, "children": { "run_training.setup": { "total": 0.0475750670002526, "count": 1, "self": 0.0475750670002526 }, "TrainerController.start_learning": { "total": 2186.1807382459997, "count": 1, "self": 1.342350037979486, "children": { "TrainerController._reset_env": { "total": 5.1781724290003694, "count": 1, "self": 5.1781724290003694 }, "TrainerController.advance": { "total": 2179.564462146019, "count": 63625, "self": 1.3837121629612739, "children": { "env_step": { "total": 1504.620007562948, "count": 63625, "self": 1396.8218963300756, "children": { "SubprocessEnvManager._take_step": { "total": 107.00243876199784, "count": 63625, "self": 4.71773182105062, "children": { "TorchPolicy.evaluate": { "total": 102.28470694094722, "count": 62562, "self": 102.28470694094722 } } }, "workers": { "total": 0.795672470874706, "count": 63625, "self": 0.0, "children": { "worker_root": { "total": 2181.3918014019696, "count": 63625, "is_parallel": true, "self": 895.5113775699751, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025771829996301676, "count": 1, "is_parallel": true, "self": 0.0007210119993033004, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018561710003268672, "count": 8, "is_parallel": true, "self": 0.0018561710003268672 } } }, "UnityEnvironment.step": { "total": 0.0768943240000226, "count": 1, "is_parallel": true, "self": 0.0007364729999608244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005928890000177489, "count": 1, "is_parallel": true, "self": 0.0005928890000177489 }, "communicator.exchange": { "total": 0.07347017800020694, "count": 1, "is_parallel": true, "self": 0.07347017800020694 }, "steps_from_proto": { "total": 0.002094783999837091, "count": 1, "is_parallel": true, "self": 0.0004342669994912285, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016605170003458625, "count": 8, "is_parallel": true, "self": 0.0016605170003458625 } } } } } } }, "UnityEnvironment.step": { "total": 1285.8804238319944, "count": 63624, "is_parallel": true, "self": 34.021857145067315, "children": { "UnityEnvironment._generate_step_input": { "total": 23.41696516900629, "count": 63624, "is_parallel": true, "self": 23.41696516900629 }, "communicator.exchange": { "total": 1128.2645958019393, "count": 63624, "is_parallel": true, "self": 1128.2645958019393 }, "steps_from_proto": { "total": 100.17700571598152, "count": 63624, "is_parallel": true, "self": 19.82227824415895, "children": { "_process_rank_one_or_two_observation": { "total": 80.35472747182257, "count": 508992, "is_parallel": true, "self": 80.35472747182257 } } } } } } } } } } }, "trainer_advance": { "total": 673.5607424201098, "count": 63625, "self": 2.308553580149237, "children": { "process_trajectory": { "total": 109.8469799499594, "count": 63625, "self": 109.64408902696005, "children": { "RLTrainer._checkpoint": { "total": 0.20289092299935874, "count": 2, "self": 0.20289092299935874 } } }, "_update_policy": { "total": 561.4052088900012, "count": 443, "self": 365.2058633520478, "children": { "TorchPPOOptimizer.update": { "total": 196.19934553795338, "count": 22827, "self": 196.19934553795338 } } } } } } }, "trainer_threads": { "total": 8.820006769383326e-07, "count": 1, "self": 8.820006769383326e-07 }, "TrainerController._save_models": { "total": 0.09575275099996361, "count": 1, "self": 0.0012842859996453626, "children": { "RLTrainer._checkpoint": { "total": 0.09446846500031825, "count": 1, "self": 0.09446846500031825 } } } } } } }