{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": -0.08906658738851547, "min": -0.10712047666311264, "max": 1.3384947776794434, "count": 167 }, "Worm.Policy.Entropy.sum": { "value": -2671.99755859375, "min": -3213.6142578125, "max": 40154.84375, "count": 167 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 167 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 167 }, "Worm.Step.mean": { "value": 5009000.0, "min": 29000.0, "max": 5009000.0, "count": 167 }, "Worm.Step.sum": { "value": 5009000.0, "min": 29000.0, "max": 5009000.0, "count": 167 }, "Worm.Policy.ExtrinsicValue.mean": { "value": 203.8448944091797, "min": 15.553304672241211, "max": 204.15045166015625, "count": 167 }, "Worm.Policy.ExtrinsicValue.sum": { "value": 6115.3466796875, "min": 451.04583740234375, "max": 6124.513671875, "count": 167 }, "Worm.Environment.CumulativeReward.mean": { "value": 1155.841288248698, "min": 0.6933828540922453, "max": 1198.7954833984375, "count": 167 }, "Worm.Environment.CumulativeReward.sum": { "value": 34675.23864746094, "min": 20.80148562276736, "max": 35963.864501953125, "count": 167 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 1155.841288248698, "min": 0.6933828540922453, "max": 1198.7954833984375, "count": 167 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 34675.23864746094, "min": 20.80148562276736, "max": 35963.864501953125, "count": 167 }, "Worm.Losses.PolicyLoss.mean": { "value": -204.19466679053937, "min": -204.19466679053937, "max": -15.437157322180587, "count": 167 }, "Worm.Losses.PolicyLoss.sum": { "value": -306292.00018580904, "min": -306292.00018580904, "max": -15421.720164858407, "count": 167 }, "Worm.Losses.ValueLoss.mean": { "value": 0.11495992433624896, "min": 0.0021663563873678795, "max": 0.7470005407847936, "count": 167 }, "Worm.Losses.ValueLoss.sum": { "value": 172.43988650437345, "min": 3.2495345810518192, "max": 746.2535402440088, "count": 167 }, "Worm.Losses.Q1Loss.mean": { "value": 0.5074038981428377, "min": 0.0013980531849474502, "max": 0.5937736741668518, "count": 167 }, "Worm.Losses.Q1Loss.sum": { "value": 761.1058472142565, "min": 2.0970797774211754, "max": 890.6605112502776, "count": 167 }, "Worm.Losses.Q2Loss.mean": { "value": 0.5107935777027294, "min": 0.0013852412714052621, "max": 0.5926025540254107, "count": 167 }, "Worm.Losses.Q2Loss.sum": { "value": 766.190366554094, "min": 2.077861907107893, "max": 888.9038310381161, "count": 167 }, "Worm.Policy.ContinuousEntropyCoeff.mean": { "value": 0.026068585608417804, "min": 0.00024331948432407128, "max": 0.8964839441324285, "count": 167 }, "Worm.Policy.ContinuousEntropyCoeff.sum": { "value": 39.10287841262671, "min": 0.3649792264861069, "max": 928.5912170983295, "count": 167 }, "Worm.Policy.LearningRate.mean": { "value": 0.0002999999999999999, "min": 0.0002999999999999999, "max": 0.0003, "count": 167 }, "Worm.Policy.LearningRate.sum": { "value": 0.4499999999999999, "min": 0.29969999999999997, "max": 0.4499999999999999, "count": 167 }, "Worm.IsTraining.mean": { "value": 0.0, "min": 0.0, "max": 1.0, "count": 167 }, "Worm.IsTraining.sum": { "value": 0.0, "min": 0.0, "max": 1.0, "count": 167 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1660328742", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/sac/Worm.yaml --env=./trained-envs-executables/linux/Worm/Worm --run-id=Worm_poca Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1660343370" }, "total": 14627.954255591, "count": 1, "self": 0.4943431060000876, "children": { "run_training.setup": { "total": 0.09153607400003239, "count": 1, "self": 0.09153607400003239 }, "TrainerController.start_learning": { "total": 14627.368376411, "count": 1, "self": 11.014935614664864, "children": { "TrainerController._reset_env": { "total": 10.43682567199994, "count": 1, "self": 10.43682567199994 }, "TrainerController.advance": { "total": 14605.670906061336, "count": 501000, "self": 12.623936926667739, "children": { "env_step": { "total": 6116.305268104576, "count": 501000, "self": 5118.692720802552, "children": { "SubprocessEnvManager._take_step": { "total": 991.0842804979899, "count": 501000, "self": 42.741980965219796, "children": { "TorchPolicy.evaluate": { "total": 948.3422995327701, "count": 501000, "self": 165.86728738346437, "children": { "TorchPolicy.sample_actions": { "total": 782.4750121493057, "count": 501000, "self": 782.4750121493057 } } } } }, "workers": { "total": 6.5282668040341605, "count": 501000, "self": 0.0, "children": { "worker_root": { "total": 14604.288951316006, "count": 501000, "is_parallel": true, "self": 10215.657723722083, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001495592999958717, "count": 1, "is_parallel": true, "self": 0.0005225599999221231, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009730330000365939, "count": 2, "is_parallel": true, "self": 0.0009730330000365939 } } }, "UnityEnvironment.step": { "total": 0.03857344699997611, "count": 1, "is_parallel": true, "self": 0.00028638000003411435, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035323500003414665, "count": 1, "is_parallel": true, "self": 0.00035323500003414665 }, "communicator.exchange": { "total": 0.037199111999939305, "count": 1, "is_parallel": true, "self": 0.037199111999939305 }, "steps_from_proto": { "total": 0.0007347199999685472, "count": 1, "is_parallel": true, "self": 0.0003037630000335412, "children": { "_process_rank_one_or_two_observation": { "total": 0.000430956999935006, "count": 2, "is_parallel": true, "self": 0.000430956999935006 } } } } } } }, "UnityEnvironment.step": { "total": 4388.6312275939235, "count": 500999, "is_parallel": true, "self": 108.56436615572238, "children": { "UnityEnvironment._generate_step_input": { "total": 206.92136541854018, "count": 500999, "is_parallel": true, "self": 206.92136541854018 }, "communicator.exchange": { "total": 3789.646435978422, "count": 500999, "is_parallel": true, "self": 3789.646435978422 }, "steps_from_proto": { "total": 283.499060041239, "count": 500999, "is_parallel": true, "self": 123.14932970007453, "children": { "_process_rank_one_or_two_observation": { "total": 160.34973034116445, "count": 1001998, "is_parallel": true, "self": 160.34973034116445 } } } } } } } } } } }, "trainer_advance": { "total": 8476.741701030092, "count": 501000, "self": 17.138348568960282, "children": { "process_trajectory": { "total": 364.7331511191337, "count": 501000, "self": 362.4332111081344, "children": { "RLTrainer._checkpoint": { "total": 2.2999400109993076, "count": 10, "self": 2.2999400109993076 } } }, "_update_policy": { "total": 8094.870201341998, "count": 500000, "self": 4.228540632383556, "children": { "SACTrainer._update_policy": { "total": 8090.641660709614, "count": 500000, "self": 2867.900305122679, "children": { "TorchSACOptimizer.update": { "total": 5222.741355586935, "count": 249999, "self": 5222.741355586935 } } } } } } } } }, "trainer_threads": { "total": 1.2589989637490362e-06, "count": 1, "self": 1.2589989637490362e-06 }, "TrainerController._save_models": { "total": 0.24570780399881187, "count": 1, "self": 0.0028128199992352165, "children": { "RLTrainer._checkpoint": { "total": 0.24289498399957665, "count": 1, "self": 0.24289498399957665 } } } } } } }