{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8681603670120239, "min": 0.8681603670120239, "max": 2.8382341861724854, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8308.294921875, "min": 8308.294921875, "max": 29128.796875, "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": 13.166496276855469, "min": 0.37137895822525024, "max": 13.166496276855469, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2567.466796875, "min": 72.04751586914062, "max": 2662.922607421875, "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": 0.06951677939111559, "min": 0.06674165415191821, "max": 0.07195499029464783, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27806711756446234, "min": 0.2685564856852437, "max": 0.3597749514732391, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16236533591268107, "min": 0.13147999185283538, "max": 0.2785307043206458, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6494613436507243, "min": 0.5259199674113415, "max": 1.392653521603229, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.00029188200270599996, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-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": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.004864970600000001, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.068181818181817, "min": 3.9545454545454546, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 174.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 3.9545454545454546, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 174.0, "max": 1407.0, "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": "1678482553", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/home/oem/.pyenv/versions/3.9/envs/rl_class/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.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu111", "numpy_version": "1.20.3", "end_time_seconds": "1678483251" }, "total": 698.4413461849981, "count": 1, "self": 0.32081992999155773, "children": { "run_training.setup": { "total": 0.01975269000104163, "count": 1, "self": 0.01975269000104163 }, "TrainerController.start_learning": { "total": 698.1007735650055, "count": 1, "self": 0.5307044216824579, "children": { "TrainerController._reset_env": { "total": 4.7535722450047615, "count": 1, "self": 4.7535722450047615 }, "TrainerController.advance": { "total": 692.7288102223174, "count": 18210, "self": 0.22155454411404207, "children": { "env_step": { "total": 692.5072556782034, "count": 18210, "self": 541.0501576409515, "children": { "SubprocessEnvManager._take_step": { "total": 151.20956978845788, "count": 18210, "self": 1.107517399606877, "children": { "TorchPolicy.evaluate": { "total": 150.102052388851, "count": 18210, "self": 20.823455194629787, "children": { "TorchPolicy.sample_actions": { "total": 129.27859719422122, "count": 18210, "self": 129.27859719422122 } } } } }, "workers": { "total": 0.2475282487939694, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 697.4604588919319, "count": 18210, "is_parallel": true, "self": 562.8254310436387, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017273459961870685, "count": 1, "is_parallel": true, "self": 0.0005367640114855021, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011905819847015664, "count": 10, "is_parallel": true, "self": 0.0011905819847015664 } } }, "UnityEnvironment.step": { "total": 0.022449436997703742, "count": 1, "is_parallel": true, "self": 0.0005928509999648668, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036864700086880475, "count": 1, "is_parallel": true, "self": 0.00036864700086880475 }, "communicator.exchange": { "total": 0.02007245300046634, "count": 1, "is_parallel": true, "self": 0.02007245300046634 }, "steps_from_proto": { "total": 0.0014154859964037314, "count": 1, "is_parallel": true, "self": 0.0003168079856550321, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010986780107486993, "count": 10, "is_parallel": true, "self": 0.0010986780107486993 } } } } } } }, "UnityEnvironment.step": { "total": 134.63502784829325, "count": 18209, "is_parallel": true, "self": 6.302779663645197, "children": { "UnityEnvironment._generate_step_input": { "total": 3.8664049813960446, "count": 18209, "is_parallel": true, "self": 3.8664049813960446 }, "communicator.exchange": { "total": 105.11752805464494, "count": 18209, "is_parallel": true, "self": 105.11752805464494 }, "steps_from_proto": { "total": 19.34831514860707, "count": 18209, "is_parallel": true, "self": 4.379620624706149, "children": { "_process_rank_one_or_two_observation": { "total": 14.968694523900922, "count": 182090, "is_parallel": true, "self": 14.968694523900922 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.645200043451041e-05, "count": 1, "self": 9.645200043451041e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 676.4614180560893, "count": 210908, "is_parallel": true, "self": 5.889283367308963, "children": { "process_trajectory": { "total": 199.27427101277135, "count": 210908, "is_parallel": true, "self": 198.34872211277252, "children": { "RLTrainer._checkpoint": { "total": 0.9255488999988302, "count": 4, "is_parallel": true, "self": 0.9255488999988302 } } }, "_update_policy": { "total": 471.297863676009, "count": 90, "is_parallel": true, "self": 154.60499571461696, "children": { "TorchPPOOptimizer.update": { "total": 316.69286796139204, "count": 22935, "is_parallel": true, "self": 316.69286796139204 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08759022400045069, "count": 1, "self": 0.0007683119983994402, "children": { "RLTrainer._checkpoint": { "total": 0.08682191200205125, "count": 1, "self": 0.08682191200205125 } } } } } } }