{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 1.2281074523925781, "min": 1.2281074523925781, "max": 1.428634762763977, "count": 83 }, "Worm.Policy.Entropy.sum": { "value": 36843.22265625, "min": 36843.22265625, "max": 42859.04296875, "count": 83 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 83 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 83 }, "Worm.Step.mean": { "value": 2999000.0, "min": 539000.0, "max": 2999000.0, "count": 83 }, "Worm.Step.sum": { "value": 2999000.0, "min": 539000.0, "max": 2999000.0, "count": 83 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 99.37371063232422, "min": 0.34739580750465393, "max": 99.37371063232422, "count": 83 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 2981.21142578125, "min": 10.074478149414062, "max": 2981.21142578125, "count": 83 }, "Worm.Environment.CumulativeReward.mean": { "value": 520.6037302652995, "min": 3.463860376127835, "max": 520.6037302652995, "count": 83 }, "Worm.Environment.CumulativeReward.sum": { "value": 15618.111907958984, "min": 100.45195090770721, "max": 15618.111907958984, "count": 83 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 520.6037302652995, "min": 3.463860376127835, "max": 520.6037302652995, "count": 83 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 15618.111907958984, "min": 100.45195090770721, "max": 15618.111907958984, "count": 83 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 83 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 83 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.016494595878092305, "min": 0.012496019920079215, "max": 0.02171410416901511, "count": 82 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.016494595878092305, "min": 0.012496019920079215, "max": 0.02171410416901511, "count": 82 }, "Worm.Losses.ValueLoss.mean": { "value": 5.932112194242931, "min": 0.015786553112169106, "max": 7.489530790419805, "count": 82 }, "Worm.Losses.ValueLoss.sum": { "value": 5.932112194242931, "min": 0.015786553112169106, "max": 7.489530790419805, "count": 82 }, "Worm.Policy.LearningRate.mean": { "value": 3.0000990000000026e-06, "min": 3.0000990000000026e-06, "max": 0.00024600001800000005, "count": 82 }, "Worm.Policy.LearningRate.sum": { "value": 3.0000990000000026e-06, "min": 3.0000990000000026e-06, "max": 0.00024600001800000005, "count": 82 }, "Worm.Policy.Epsilon.mean": { "value": 0.101, "min": 0.101, "max": 0.18200000000000005, "count": 82 }, "Worm.Policy.Epsilon.sum": { "value": 0.101, "min": 0.101, "max": 0.18200000000000005, "count": 82 }, "Worm.Policy.Beta.mean": { "value": 5.990000000000004e-05, "min": 5.990000000000004e-05, "max": 0.004101799999999999, "count": 82 }, "Worm.Policy.Beta.sum": { "value": 5.990000000000004e-05, "min": 5.990000000000004e-05, "max": 0.004101799999999999, "count": 82 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1662408137", "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/ppo/Worm.yaml --env=./trained-envs-executables/linux/Worm/Worm --run-id=Worm Training --no-graphics --resume", "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": "1662411364" }, "total": 3227.223342972, "count": 1, "self": 0.4319030539995765, "children": { "run_training.setup": { "total": 0.04244852900001206, "count": 1, "self": 0.04244852900001206 }, "TrainerController.start_learning": { "total": 3226.7489913890004, "count": 1, "self": 5.011138950077566, "children": { "TrainerController._reset_env": { "total": 5.522024972000054, "count": 1, "self": 5.522024972000054 }, "TrainerController.advance": { "total": 3216.0898506789226, "count": 250000, "self": 5.196725621778114, "children": { "env_step": { "total": 2633.163532223111, "count": 250000, "self": 2305.8082285332166, "children": { "SubprocessEnvManager._take_step": { "total": 324.3323897798223, "count": 250000, "self": 22.1403746578103, "children": { "TorchPolicy.evaluate": { "total": 302.192015122012, "count": 250000, "self": 76.07665375211377, "children": { "TorchPolicy.sample_actions": { "total": 226.1153613698982, "count": 250000, "self": 226.1153613698982 } } } } }, "workers": { "total": 3.022913910071793, "count": 250000, "self": 0.0, "children": { "worker_root": { "total": 3217.189885740073, "count": 250000, "is_parallel": true, "self": 1217.5168594330783, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001029897000080382, "count": 1, "is_parallel": true, "self": 0.00032974900022963993, "children": { "_process_rank_one_or_two_observation": { "total": 0.000700147999850742, "count": 2, "is_parallel": true, "self": 0.000700147999850742 } } }, "UnityEnvironment.step": { "total": 0.02948732899994866, "count": 1, "is_parallel": true, "self": 0.00021975100003146508, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040555400005359843, "count": 1, "is_parallel": true, "self": 0.00040555400005359843 }, "communicator.exchange": { "total": 0.028275719000021127, "count": 1, "is_parallel": true, "self": 0.028275719000021127 }, "steps_from_proto": { "total": 0.0005863049998424685, "count": 1, "is_parallel": true, "self": 0.00021804899984090298, "children": { "_process_rank_one_or_two_observation": { "total": 0.00036825600000156555, "count": 2, "is_parallel": true, "self": 0.00036825600000156555 } } } } } } }, "UnityEnvironment.step": { "total": 1999.6730263069946, "count": 249999, "is_parallel": true, "self": 42.278463598850976, "children": { "UnityEnvironment._generate_step_input": { "total": 76.01717416214797, "count": 249999, "is_parallel": true, "self": 76.01717416214797 }, "communicator.exchange": { "total": 1769.8692639030182, "count": 249999, "is_parallel": true, "self": 1769.8692639030182 }, "steps_from_proto": { "total": 111.50812464297746, "count": 249999, "is_parallel": true, "self": 44.33241369017401, "children": { "_process_rank_one_or_two_observation": { "total": 67.17571095280346, "count": 499998, "is_parallel": true, "self": 67.17571095280346 } } } } } } } } } } }, "trainer_advance": { "total": 577.7295928340336, "count": 250000, "self": 6.568939747116701, "children": { "process_trajectory": { "total": 166.98389703791872, "count": 250000, "self": 166.366754103919, "children": { "RLTrainer._checkpoint": { "total": 0.6171429339997303, "count": 5, "self": 0.6171429339997303 } } }, "_update_policy": { "total": 404.1767560489982, "count": 83, "self": 352.00662608197695, "children": { "TorchPPOOptimizer.update": { "total": 52.17012996702124, "count": 3486, "self": 52.17012996702124 } } } } } } }, "trainer_threads": { "total": 1.1989995982730761e-06, "count": 1, "self": 1.1989995982730761e-06 }, "TrainerController._save_models": { "total": 0.12597558900051808, "count": 1, "self": 0.003015911000147753, "children": { "RLTrainer._checkpoint": { "total": 0.12295967800037033, "count": 1, "self": 0.12295967800037033 } } } } } } }