{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 1.0663478374481201, "min": 1.0663478374481201, "max": 1.418938398361206, "count": 133 }, "Worm.Policy.Entropy.sum": { "value": 31990.43359375, "min": 31990.43359375, "max": 42568.15234375, "count": 133 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 133 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 133 }, "Worm.Step.mean": { "value": 3989000.0, "min": 29000.0, "max": 3989000.0, "count": 133 }, "Worm.Step.sum": { "value": 3989000.0, "min": 29000.0, "max": 3989000.0, "count": 133 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 152.24058532714844, "min": -0.013336945325136185, "max": 152.24058532714844, "count": 133 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 4567.2177734375, "min": -0.38677141070365906, "max": 4567.2177734375, "count": 133 }, "Worm.Environment.CumulativeReward.mean": { "value": 782.232725016276, "min": 0.28914098516106607, "max": 782.5456156412761, "count": 133 }, "Worm.Environment.CumulativeReward.sum": { "value": 23466.98175048828, "min": 8.674229554831982, "max": 23476.36846923828, "count": 133 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 782.232725016276, "min": 0.28914098516106607, "max": 782.5456156412761, "count": 133 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 23466.98175048828, "min": 8.674229554831982, "max": 23476.36846923828, "count": 133 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 133 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 133 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.015966338155392026, "min": 0.013125823902165783, "max": 0.022229330883073134, "count": 132 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.015966338155392026, "min": 0.013125823902165783, "max": 0.022229330883073134, "count": 132 }, "Worm.Losses.ValueLoss.mean": { "value": 9.144103129704794, "min": 0.0015650599601767247, "max": 9.262617429097494, "count": 132 }, "Worm.Losses.ValueLoss.sum": { "value": 9.144103129704794, "min": 0.0015650599601767247, "max": 9.262617429097494, "count": 132 }, "Worm.Policy.LearningRate.mean": { "value": 3.0000990000000026e-06, "min": 3.0000990000000026e-06, "max": 0.00029775000075, "count": 132 }, "Worm.Policy.LearningRate.sum": { "value": 3.0000990000000026e-06, "min": 3.0000990000000026e-06, "max": 0.00029775000075, "count": 132 }, "Worm.Policy.Epsilon.mean": { "value": 0.101, "min": 0.101, "max": 0.19924999999999998, "count": 132 }, "Worm.Policy.Epsilon.sum": { "value": 0.101, "min": 0.101, "max": 0.19924999999999998, "count": 132 }, "Worm.Policy.Beta.mean": { "value": 5.990000000000004e-05, "min": 5.990000000000004e-05, "max": 0.004962575, "count": 132 }, "Worm.Policy.Beta.sum": { "value": 5.990000000000004e-05, "min": 5.990000000000004e-05, "max": 0.004962575, "count": 132 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739384855", "python_version": "3.10.12 (main, Jan 17 2025, 14:35:34) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=../training-envs-executables/linux/Worm/Worm --run-id=Worm1 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739389937" }, "total": 5081.980067805009, "count": 1, "self": 0.3684676999982912, "children": { "run_training.setup": { "total": 0.01631790300598368, "count": 1, "self": 0.01631790300598368 }, "TrainerController.start_learning": { "total": 5081.5952822020045, "count": 1, "self": 6.492803135333816, "children": { "TrainerController._reset_env": { "total": 7.49838720500702, "count": 1, "self": 7.49838720500702 }, "TrainerController.advance": { "total": 5067.500726156664, "count": 401000, "self": 5.571857859467855, "children": { "env_step": { "total": 4551.262668966287, "count": 401000, "self": 3480.4544615204213, "children": { "SubprocessEnvManager._take_step": { "total": 1066.1893351739272, "count": 401000, "self": 21.103722016123356, "children": { "TorchPolicy.evaluate": { "total": 1045.085613157804, "count": 401000, "self": 1045.085613157804 } } }, "workers": { "total": 4.618872271938017, "count": 401000, "self": 0.0, "children": { "worker_root": { "total": 5066.994436412206, "count": 401000, "is_parallel": true, "self": 1914.0149631741806, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006424080056603998, "count": 1, "is_parallel": true, "self": 0.00015990299289114773, "children": { "_process_rank_one_or_two_observation": { "total": 0.00048250501276925206, "count": 2, "is_parallel": true, "self": 0.00048250501276925206 } } }, "UnityEnvironment.step": { "total": 0.01703754998743534, "count": 1, "is_parallel": true, "self": 0.00010400600149296224, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001749119837768376, "count": 1, "is_parallel": true, "self": 0.0001749119837768376 }, "communicator.exchange": { "total": 0.01635050799814053, "count": 1, "is_parallel": true, "self": 0.01635050799814053 }, "steps_from_proto": { "total": 0.00040812400402501225, "count": 1, "is_parallel": true, "self": 0.00017267698422074318, "children": { "_process_rank_one_or_two_observation": { "total": 0.00023544701980426908, "count": 2, "is_parallel": true, "self": 0.00023544701980426908 } } } } } } }, "UnityEnvironment.step": { "total": 3152.979473238025, "count": 400999, "is_parallel": true, "self": 33.303838305408135, "children": { "UnityEnvironment._generate_step_input": { "total": 42.738952677027555, "count": 400999, "is_parallel": true, "self": 42.738952677027555 }, "communicator.exchange": { "total": 2997.1447735649417, "count": 400999, "is_parallel": true, "self": 2997.1447735649417 }, "steps_from_proto": { "total": 79.79190869064769, "count": 400999, "is_parallel": true, "self": 22.407319652469596, "children": { "_process_rank_one_or_two_observation": { "total": 57.38458903817809, "count": 801998, "is_parallel": true, "self": 57.38458903817809 } } } } } } } } } } }, "trainer_advance": { "total": 510.6661993309099, "count": 401000, "self": 10.029546890757047, "children": { "process_trajectory": { "total": 129.0715786649671, "count": 401000, "self": 128.3616090149735, "children": { "RLTrainer._checkpoint": { "total": 0.7099696499935817, "count": 8, "self": 0.7099696499935817 } } }, "_update_policy": { "total": 371.56507377518574, "count": 133, "self": 227.08188193867682, "children": { "TorchPPOOptimizer.update": { "total": 144.48319183650892, "count": 5586, "self": 144.48319183650892 } } } } } } }, "trainer_threads": { "total": 5.00993337482214e-07, "count": 1, "self": 5.00993337482214e-07 }, "TrainerController._save_models": { "total": 0.10336520400596783, "count": 1, "self": 0.0030298640194814652, "children": { "RLTrainer._checkpoint": { "total": 0.10033533998648636, "count": 1, "self": 0.10033533998648636 } } } } } } }