{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9704931378364563, "min": 0.9704931378364563, "max": 2.870173692703247, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9266.2685546875, "min": 9266.2685546875, "max": 29425.01953125, "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": 12.886282920837402, "min": 0.32998237013816833, "max": 12.937592506408691, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2512.8251953125, "min": 64.0165786743164, "max": 2639.268798828125, "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": 0.06374453301381722, "min": 0.0632521510272579, "max": 0.07277589831683859, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25497813205526887, "min": 0.2530086041090316, "max": 0.3638794915841929, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2106827712964778, "min": 0.12592381741006986, "max": 0.2742601474710539, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8427310851859112, "min": 0.5036952696402794, "max": 1.3713007373552695, "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": 24.681818181818183, "min": 3.522727272727273, "max": 25.672727272727272, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1086.0, "min": 155.0, "max": 1412.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.681818181818183, "min": 3.522727272727273, "max": 25.672727272727272, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1086.0, "min": 155.0, "max": 1412.0, "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": "1678936426", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678937065" }, "total": 639.402323764, "count": 1, "self": 0.546247977999883, "children": { "run_training.setup": { "total": 0.2297264090000226, "count": 1, "self": 0.2297264090000226 }, "TrainerController.start_learning": { "total": 638.6263493770001, "count": 1, "self": 0.9275116909936969, "children": { "TrainerController._reset_env": { "total": 10.163402569000027, "count": 1, "self": 10.163402569000027 }, "TrainerController.advance": { "total": 627.3742453100064, "count": 18202, "self": 0.5241723469949875, "children": { "env_step": { "total": 626.8500729630114, "count": 18202, "self": 500.71662194500436, "children": { "SubprocessEnvManager._take_step": { "total": 125.68376798500219, "count": 18202, "self": 3.8105810800133213, "children": { "TorchPolicy.evaluate": { "total": 121.87318690498887, "count": 18202, "self": 121.87318690498887 } } }, "workers": { "total": 0.44968303300481693, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 636.1529931409948, "count": 18202, "is_parallel": true, "self": 287.2453358110047, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009533018000070115, "count": 1, "is_parallel": true, "self": 0.006166870000129165, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033661479999409494, "count": 10, "is_parallel": true, "self": 0.0033661479999409494 } } }, "UnityEnvironment.step": { "total": 0.047054036999952586, "count": 1, "is_parallel": true, "self": 0.0008017330000029688, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004612279999491875, "count": 1, "is_parallel": true, "self": 0.0004612279999491875 }, "communicator.exchange": { "total": 0.043379931000004035, "count": 1, "is_parallel": true, "self": 0.043379931000004035 }, "steps_from_proto": { "total": 0.002411144999996395, "count": 1, "is_parallel": true, "self": 0.00047637099964958907, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019347740003468061, "count": 10, "is_parallel": true, "self": 0.0019347740003468061 } } } } } } }, "UnityEnvironment.step": { "total": 348.9076573299901, "count": 18201, "is_parallel": true, "self": 14.00073250398998, "children": { "UnityEnvironment._generate_step_input": { "total": 7.6498818529892105, "count": 18201, "is_parallel": true, "self": 7.6498818529892105 }, "communicator.exchange": { "total": 280.77315285700695, "count": 18201, "is_parallel": true, "self": 280.77315285700695 }, "steps_from_proto": { "total": 46.48389011600398, "count": 18201, "is_parallel": true, "self": 9.771929876033823, "children": { "_process_rank_one_or_two_observation": { "total": 36.71196023997015, "count": 182010, "is_parallel": true, "self": 36.71196023997015 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002433649999602494, "count": 1, "self": 0.0002433649999602494, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 621.0889641639552, "count": 626854, "is_parallel": true, "self": 18.2668895610243, "children": { "process_trajectory": { "total": 336.96131791093046, "count": 626854, "is_parallel": true, "self": 335.45212413993045, "children": { "RLTrainer._checkpoint": { "total": 1.5091937710000138, "count": 4, "is_parallel": true, "self": 1.5091937710000138 } } }, "_update_policy": { "total": 265.86075669200045, "count": 90, "is_parallel": true, "self": 91.93088176999584, "children": { "TorchPPOOptimizer.update": { "total": 173.92987492200461, "count": 4587, "is_parallel": true, "self": 173.92987492200461 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1609464420000677, "count": 1, "self": 0.0011495419998936995, "children": { "RLTrainer._checkpoint": { "total": 0.159796900000174, "count": 1, "self": 0.159796900000174 } } } } } } }