{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 1.3745230436325073, "min": 1.3745230436325073, "max": 1.418938398361206, "count": 33 }, "Worm.Policy.Entropy.sum": { "value": 41235.69140625, "min": 41235.69140625, "max": 42568.15234375, "count": 33 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 33 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 33 }, "Worm.Step.mean": { "value": 989000.0, "min": 29000.0, "max": 989000.0, "count": 33 }, "Worm.Step.sum": { "value": 989000.0, "min": 29000.0, "max": 989000.0, "count": 33 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 11.160162925720215, "min": -0.04857126995921135, "max": 11.160162925720215, "count": 33 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 334.8049011230469, "min": -1.4571380615234375, "max": 334.8049011230469, "count": 33 }, "Worm.Environment.CumulativeReward.mean": { "value": 98.87115840911865, "min": 0.11945420691918116, "max": 98.87115840911865, "count": 33 }, "Worm.Environment.CumulativeReward.sum": { "value": 2966.1347522735596, "min": 3.583626207575435, "max": 2966.1347522735596, "count": 33 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 98.87115840911865, "min": 0.11945420691918116, "max": 98.87115840911865, "count": 33 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 2966.1347522735596, "min": 3.583626207575435, "max": 2966.1347522735596, "count": 33 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.01527170484353389, "min": 0.014031458659831384, "max": 0.021487750632721663, "count": 32 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.01527170484353389, "min": 0.014031458659831384, "max": 0.021487750632721663, "count": 32 }, "Worm.Losses.ValueLoss.mean": { "value": 1.0280655381225405, "min": 0.0010215550844025398, "max": 1.0280655381225405, "count": 32 }, "Worm.Losses.ValueLoss.sum": { "value": 1.0280655381225405, "min": 0.0010215550844025398, "max": 1.0280655381225405, "count": 32 }, "Worm.Policy.LearningRate.mean": { "value": 1.2000096000000011e-05, "min": 1.2000096000000011e-05, "max": 0.0002910000029999999, "count": 32 }, "Worm.Policy.LearningRate.sum": { "value": 1.2000096000000011e-05, "min": 1.2000096000000011e-05, "max": 0.0002910000029999999, "count": 32 }, "Worm.Policy.Epsilon.mean": { "value": 0.10400000000000001, "min": 0.10400000000000001, "max": 0.19699999999999998, "count": 32 }, "Worm.Policy.Epsilon.sum": { "value": 0.10400000000000001, "min": 0.10400000000000001, "max": 0.19699999999999998, "count": 32 }, "Worm.Policy.Beta.mean": { "value": 0.00020960000000000022, "min": 0.00020960000000000022, "max": 0.0048503, "count": 32 }, "Worm.Policy.Beta.sum": { "value": 0.00020960000000000022, "min": 0.00020960000000000022, "max": 0.0048503, "count": 32 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1722629428", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Worm Training --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722632047" }, "total": 2618.616045187, "count": 1, "self": 0.5895694419996289, "children": { "run_training.setup": { "total": 0.07057258599979832, "count": 1, "self": 0.07057258599979832 }, "TrainerController.start_learning": { "total": 2617.9559031590006, "count": 1, "self": 3.5184329071671527, "children": { "TrainerController._reset_env": { "total": 2.115038299999469, "count": 1, "self": 2.115038299999469 }, "TrainerController.advance": { "total": 2612.202853132834, "count": 101000, "self": 3.6204221668522223, "children": { "env_step": { "total": 1783.504117572943, "count": 101000, "self": 1525.6088532438207, "children": { "SubprocessEnvManager._take_step": { "total": 255.525407303081, "count": 101000, "self": 19.630982223135106, "children": { "TorchPolicy.evaluate": { "total": 235.8944250799459, "count": 101000, "self": 235.8944250799459 } } }, "workers": { "total": 2.3698570260412453, "count": 101000, "self": 0.0, "children": { "worker_root": { "total": 2611.036638657196, "count": 101000, "is_parallel": true, "self": 1325.6193843631881, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001291333000153827, "count": 1, "is_parallel": true, "self": 0.00028855200071120635, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010027809994426207, "count": 2, "is_parallel": true, "self": 0.0010027809994426207 } } }, "UnityEnvironment.step": { "total": 0.03778330699969956, "count": 1, "is_parallel": true, "self": 0.00031413999931828585, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006524330001411727, "count": 1, "is_parallel": true, "self": 0.0006524330001411727 }, "communicator.exchange": { "total": 0.03609104200040747, "count": 1, "is_parallel": true, "self": 0.03609104200040747 }, "steps_from_proto": { "total": 0.0007256919998326339, "count": 1, "is_parallel": true, "self": 0.00023427199903380824, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004914200007988256, "count": 2, "is_parallel": true, "self": 0.0004914200007988256 } } } } } } }, "UnityEnvironment.step": { "total": 1285.4172542940078, "count": 100999, "is_parallel": true, "self": 30.023187571935523, "children": { "UnityEnvironment._generate_step_input": { "total": 44.49086723203709, "count": 100999, "is_parallel": true, "self": 44.49086723203709 }, "communicator.exchange": { "total": 1144.131780039098, "count": 100999, "is_parallel": true, "self": 1144.131780039098 }, "steps_from_proto": { "total": 66.77141945093717, "count": 100999, "is_parallel": true, "self": 20.456434648031973, "children": { "_process_rank_one_or_two_observation": { "total": 46.3149848029052, "count": 201998, "is_parallel": true, "self": 46.3149848029052 } } } } } } } } } } }, "trainer_advance": { "total": 825.078313393039, "count": 101000, "self": 4.424324589042044, "children": { "process_trajectory": { "total": 101.15340718999596, "count": 101000, "self": 100.83370532399567, "children": { "RLTrainer._checkpoint": { "total": 0.3197018660002868, "count": 2, "self": 0.3197018660002868 } } }, "_update_policy": { "total": 719.500581614001, "count": 33, "self": 179.2270422210031, "children": { "TorchPPOOptimizer.update": { "total": 540.2735393929979, "count": 1386, "self": 540.2735393929979 } } } } } } }, "trainer_threads": { "total": 9.79000105871819e-07, "count": 1, "self": 9.79000105871819e-07 }, "TrainerController._save_models": { "total": 0.11957783999969251, "count": 1, "self": 0.004787818999830051, "children": { "RLTrainer._checkpoint": { "total": 0.11479002099986246, "count": 1, "self": 0.11479002099986246 } } } } } } }