{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0433883666992188, "min": 1.0433883666992188, "max": 2.866107702255249, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10019.658203125, "min": 10019.658203125, "max": 29477.91796875, "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": 11.64319896697998, "min": 0.29731979966163635, "max": 11.64319896697998, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2270.423828125, "min": 57.68003845214844, "max": 2354.256591796875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0649339536344176, "min": 0.06331451196975632, "max": 0.07720857657113811, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2597358145376704, "min": 0.2597358145376704, "max": 0.3659756642688687, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20627333640175707, "min": 0.10024226731255503, "max": 0.2818671085086523, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8250933456070283, "min": 0.40096906925022013, "max": 1.4093355425432617, "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": 22.795454545454547, "min": 3.0, "max": 22.89090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1003.0, "min": 132.0, "max": 1259.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.795454545454547, "min": 3.0, "max": 22.89090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1003.0, "min": 132.0, "max": 1259.0, "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": "1680953716", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/home/sicong/Data/Projects/HuggingFace_DeepReinforcementLearning/venv_shared/bin/mlagents-learn ./ml-agents/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": "1680953992" }, "total": 276.45553920802195, "count": 1, "self": 0.23104855907149613, "children": { "run_training.setup": { "total": 0.018927851982880384, "count": 1, "self": 0.018927851982880384 }, "TrainerController.start_learning": { "total": 276.20556279696757, "count": 1, "self": 0.36222795164212584, "children": { "TrainerController._reset_env": { "total": 2.874545703001786, "count": 1, "self": 2.874545703001786 }, "TrainerController.advance": { "total": 272.8731447633472, "count": 18207, "self": 0.17184045910835266, "children": { "env_step": { "total": 272.7013043042389, "count": 18207, "self": 191.53122871462256, "children": { "SubprocessEnvManager._take_step": { "total": 80.99482039932627, "count": 18207, "self": 1.0212656841613352, "children": { "TorchPolicy.evaluate": { "total": 79.97355471516494, "count": 18207, "self": 79.97355471516494 } } }, "workers": { "total": 0.175255190290045, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 275.7164137745858, "count": 18207, "is_parallel": true, "self": 148.34487324481597, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011844710097648203, "count": 1, "is_parallel": true, "self": 0.0002838499494828284, "children": { "_process_rank_one_or_two_observation": { "total": 0.000900621060281992, "count": 10, "is_parallel": true, "self": 0.000900621060281992 } } }, "UnityEnvironment.step": { "total": 0.018148942035622895, "count": 1, "is_parallel": true, "self": 0.00029357109451666474, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031923101050779223, "count": 1, "is_parallel": true, "self": 0.00031923101050779223 }, "communicator.exchange": { "total": 0.01672207994852215, "count": 1, "is_parallel": true, "self": 0.01672207994852215 }, "steps_from_proto": { "total": 0.0008140599820762873, "count": 1, "is_parallel": true, "self": 0.00016186002176254988, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006521999603137374, "count": 10, "is_parallel": true, "self": 0.0006521999603137374 } } } } } } }, "UnityEnvironment.step": { "total": 127.37154052976985, "count": 18206, "is_parallel": true, "self": 6.373761402908713, "children": { "UnityEnvironment._generate_step_input": { "total": 3.509863027720712, "count": 18206, "is_parallel": true, "self": 3.509863027720712 }, "communicator.exchange": { "total": 100.90063007123535, "count": 18206, "is_parallel": true, "self": 100.90063007123535 }, "steps_from_proto": { "total": 16.587286027905066, "count": 18206, "is_parallel": true, "self": 3.0507068094448186, "children": { "_process_rank_one_or_two_observation": { "total": 13.536579218460247, "count": 182060, "is_parallel": true, "self": 13.536579218460247 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.751098696142435e-05, "count": 1, "self": 9.751098696142435e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 272.4809430191526, "count": 177109, "is_parallel": true, "self": 1.7672462473856285, "children": { "process_trajectory": { "total": 148.13617796229664, "count": 177109, "is_parallel": true, "self": 147.62857006129343, "children": { "RLTrainer._checkpoint": { "total": 0.5076079010032117, "count": 4, "is_parallel": true, "self": 0.5076079010032117 } } }, "_update_policy": { "total": 122.57751880947035, "count": 90, "is_parallel": true, "self": 32.52505401574308, "children": { "TorchPPOOptimizer.update": { "total": 90.05246479372727, "count": 4587, "is_parallel": true, "self": 90.05246479372727 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09554686798946932, "count": 1, "self": 0.0006944519700482488, "children": { "RLTrainer._checkpoint": { "total": 0.09485241601942107, "count": 1, "self": 0.09485241601942107 } } } } } } }