{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9422158598899841, "min": 0.9422158598899841, "max": 2.8643853664398193, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9006.6416015625, "min": 9006.6416015625, "max": 29397.1875, "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": 13.074606895446777, "min": 0.4222770631313324, "max": 13.074606895446777, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2549.54833984375, "min": 81.9217529296875, "max": 2662.3095703125, "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": 0.06826644771710705, "min": 0.06440964992085071, "max": 0.07603559602535895, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2730657908684282, "min": 0.27162216846858533, "max": 0.38017798012679477, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20119947034354302, "min": 0.12894852624466532, "max": 0.3005658260601409, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8047978813741721, "min": 0.5157941049786613, "max": 1.5028291303007044, "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": 25.522727272727273, "min": 3.409090909090909, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 150.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 3.409090909090909, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 150.0, "max": 1428.0, "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": "1679925845", "python_version": "3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0]", "command_line_arguments": "/home/alertrack/.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": "1679926082" }, "total": 237.1665234779939, "count": 1, "self": 0.2687603207305074, "children": { "run_training.setup": { "total": 0.015522031113505363, "count": 1, "self": 0.015522031113505363 }, "TrainerController.start_learning": { "total": 236.8822411261499, "count": 1, "self": 0.3451485666446388, "children": { "TrainerController._reset_env": { "total": 11.923782124649733, "count": 1, "self": 11.923782124649733 }, "TrainerController.advance": { "total": 224.5220189797692, "count": 18202, "self": 0.17666083248332143, "children": { "env_step": { "total": 224.34535814728588, "count": 18202, "self": 170.1183779258281, "children": { "SubprocessEnvManager._take_step": { "total": 54.04141727928072, "count": 18202, "self": 1.0430521462112665, "children": { "TorchPolicy.evaluate": { "total": 52.998365133069456, "count": 18202, "self": 52.998365133069456 } } }, "workers": { "total": 0.18556294217705727, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 236.3767926413566, "count": 18202, "is_parallel": true, "self": 114.98955691838637, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013147732242941856, "count": 1, "is_parallel": true, "self": 0.0003544469363987446, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009603262878954411, "count": 10, "is_parallel": true, "self": 0.0009603262878954411 } } }, "UnityEnvironment.step": { "total": 0.018401720095425844, "count": 1, "is_parallel": true, "self": 0.0002546044997870922, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016577495262026787, "count": 1, "is_parallel": true, "self": 0.00016577495262026787 }, "communicator.exchange": { "total": 0.017091226764023304, "count": 1, "is_parallel": true, "self": 0.017091226764023304 }, "steps_from_proto": { "total": 0.0008901138789951801, "count": 1, "is_parallel": true, "self": 0.00020392565056681633, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006861882284283638, "count": 10, "is_parallel": true, "self": 0.0006861882284283638 } } } } } } }, "UnityEnvironment.step": { "total": 121.38723572297022, "count": 18201, "is_parallel": true, "self": 4.473253517411649, "children": { "UnityEnvironment._generate_step_input": { "total": 2.477889238856733, "count": 18201, "is_parallel": true, "self": 2.477889238856733 }, "communicator.exchange": { "total": 99.32827112311497, "count": 18201, "is_parallel": true, "self": 99.32827112311497 }, "steps_from_proto": { "total": 15.107821843586862, "count": 18201, "is_parallel": true, "self": 3.1415507355704904, "children": { "_process_rank_one_or_two_observation": { "total": 11.966271108016372, "count": 182010, "is_parallel": true, "self": 11.966271108016372 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.876815602183342e-05, "count": 1, "self": 9.876815602183342e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 224.20664708828554, "count": 151323, "is_parallel": true, "self": 1.657522851601243, "children": { "process_trajectory": { "total": 117.30007063644007, "count": 151323, "is_parallel": true, "self": 116.77668167231604, "children": { "RLTrainer._checkpoint": { "total": 0.5233889641240239, "count": 4, "is_parallel": true, "self": 0.5233889641240239 } } }, "_update_policy": { "total": 105.24905360024422, "count": 90, "is_parallel": true, "self": 32.241208089049906, "children": { "TorchPPOOptimizer.update": { "total": 73.00784551119432, "count": 4584, "is_parallel": true, "self": 73.00784551119432 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0911926869302988, "count": 1, "self": 0.0005851718597114086, "children": { "RLTrainer._checkpoint": { "total": 0.0906075150705874, "count": 1, "self": 0.0906075150705874 } } } } } } }