{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9599742293357849, "min": 0.9599742293357849, "max": 2.8642382621765137, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9186.953125, "min": 9186.953125, "max": 29364.171875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.905156135559082, "min": 0.4550105929374695, "max": 12.905156135559082, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.50537109375, "min": 88.27205657958984, "max": 2626.411376953125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06481513670209381, "min": 0.05836469656605201, "max": 0.07381915491258077, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25926054680837524, "min": 0.2487495287079547, "max": 0.358215236423455, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17167581055386394, "min": 0.13756993694194392, "max": 0.29583681791144256, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6867032422154558, "min": 0.5502797477677757, "max": 1.465831429934969, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.681818181818183, "min": 3.9318181818181817, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1130.0, "min": 173.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.681818181818183, "min": 3.9318181818181817, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1130.0, "min": 173.0, "max": 1399.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675516701", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:06) \n[GCC 11.3.0]", "command_line_arguments": "/home/antoine/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.29.0", "mlagents_envs_version": "0.29.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1675517026" }, "total": 325.27983902099993, "count": 1, "self": 0.16744304199983162, "children": { "run_training.setup": { "total": 0.015722265000022162, "count": 1, "self": 0.015722265000022162 }, "TrainerController.start_learning": { "total": 325.0966737140001, "count": 1, "self": 0.281043649003891, "children": { "TrainerController._reset_env": { "total": 1.4558530060000976, "count": 1, "self": 1.4558530060000976 }, "TrainerController.advance": { "total": 323.30135927099604, "count": 18202, "self": 0.1330064570046261, "children": { "env_step": { "total": 323.1683528139914, "count": 18202, "self": 194.13691393500517, "children": { "SubprocessEnvManager._take_step": { "total": 128.9003132639965, "count": 18202, "self": 0.8136755170039578, "children": { "TorchPolicy.evaluate": { "total": 128.08663774699255, "count": 18202, "self": 39.08961608798904, "children": { "TorchPolicy.sample_actions": { "total": 88.99702165900351, "count": 18202, "self": 88.99702165900351 } } } } }, "workers": { "total": 0.13112561498974173, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 324.4776129659954, "count": 18202, "is_parallel": true, "self": 183.82294706099322, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001102097000057256, "count": 1, "is_parallel": true, "self": 0.0003455369999301183, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007565600001271378, "count": 10, "is_parallel": true, "self": 0.0007565600001271378 } } }, "UnityEnvironment.step": { "total": 0.01870673199994144, "count": 1, "is_parallel": true, "self": 0.0001921669999092046, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018648799994025467, "count": 1, "is_parallel": true, "self": 0.00018648799994025467 }, "communicator.exchange": { "total": 0.017633325000019795, "count": 1, "is_parallel": true, "self": 0.017633325000019795 }, "steps_from_proto": { "total": 0.0006947520000721852, "count": 1, "is_parallel": true, "self": 0.00015458899997611297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005401630000960722, "count": 10, "is_parallel": true, "self": 0.0005401630000960722 } } } } } } }, "UnityEnvironment.step": { "total": 140.65466590500216, "count": 18201, "is_parallel": true, "self": 3.3034600870023496, "children": { "UnityEnvironment._generate_step_input": { "total": 1.8405812859959951, "count": 18201, "is_parallel": true, "self": 1.8405812859959951 }, "communicator.exchange": { "total": 125.30160283699911, "count": 18201, "is_parallel": true, "self": 125.30160283699911 }, "steps_from_proto": { "total": 10.209021695004708, "count": 18201, "is_parallel": true, "self": 2.2363757910372897, "children": { "_process_rank_one_or_two_observation": { "total": 7.972645903967418, "count": 182010, "is_parallel": true, "self": 7.972645903967418 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017921800008480204, "count": 1, "self": 0.00017921800008480204, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 321.44778936797456, "count": 344121, "is_parallel": true, "self": 5.526480144052584, "children": { "process_trajectory": { "total": 167.65012914192118, "count": 344121, "is_parallel": true, "self": 167.28418962292108, "children": { "RLTrainer._checkpoint": { "total": 0.3659395190001078, "count": 4, "is_parallel": true, "self": 0.3659395190001078 } } }, "_update_policy": { "total": 148.2711800820008, "count": 90, "is_parallel": true, "self": 22.43410220599992, "children": { "TorchPPOOptimizer.update": { "total": 125.83707787600088, "count": 4587, "is_parallel": true, "self": 125.83707787600088 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05823856999995769, "count": 1, "self": 0.0007232919999751175, "children": { "RLTrainer._checkpoint": { "total": 0.05751527799998257, "count": 1, "self": 0.05751527799998257 } } } } } } }