{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1237443685531616, "min": 1.1237443685531616, "max": 2.8504152297973633, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10754.2333984375, "min": 10754.2333984375, "max": 29222.45703125, "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": 11.614886283874512, "min": 0.43102267384529114, "max": 11.614886283874512, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2264.90283203125, "min": 83.61840057373047, "max": 2333.810791015625, "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": 0.06570940507734514, "min": 0.06106924022081811, "max": 0.07402926603361837, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26283762030938057, "min": 0.24427696088327244, "max": 0.3680490115132439, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18228381214772954, "min": 0.1403834389764633, "max": 0.27825765861015694, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7291352485909182, "min": 0.5615337559058532, "max": 1.3912882930507846, "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": 23.34090909090909, "min": 3.8636363636363638, "max": 23.34090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1027.0, "min": 170.0, "max": 1268.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.34090909090909, "min": 3.8636363636363638, "max": 23.34090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1027.0, "min": 170.0, "max": 1268.0, "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": "1673775769", "python_version": "3.8.13 (default, Mar 28 2022, 11:38:47) \n[GCC 7.5.0]", "command_line_arguments": "/data1/zhenhuan_liu/anaconda3/envs/RL/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.23.0", "end_time_seconds": "1673776334" }, "total": 564.4623995572329, "count": 1, "self": 0.3225214555859566, "children": { "run_training.setup": { "total": 0.024620432406663895, "count": 1, "self": 0.024620432406663895 }, "TrainerController.start_learning": { "total": 564.1152576692402, "count": 1, "self": 0.47332795709371567, "children": { "TrainerController._reset_env": { "total": 2.1684222407639027, "count": 1, "self": 2.1684222407639027 }, "TrainerController.advance": { "total": 561.4020166806877, "count": 18203, "self": 0.2268051691353321, "children": { "env_step": { "total": 561.1752115115523, "count": 18203, "self": 475.9460798688233, "children": { "SubprocessEnvManager._take_step": { "total": 85.02812844887376, "count": 18203, "self": 1.212802231311798, "children": { "TorchPolicy.evaluate": { "total": 83.81532621756196, "count": 18203, "self": 17.013007927685976, "children": { "TorchPolicy.sample_actions": { "total": 66.80231828987598, "count": 18203, "self": 66.80231828987598 } } } } }, "workers": { "total": 0.20100319385528564, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 562.8091255016625, "count": 18203, "is_parallel": true, "self": 196.09069154784083, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0042130351066589355, "count": 1, "is_parallel": true, "self": 0.0011581815779209137, "children": { "_process_rank_one_or_two_observation": { "total": 0.003054853528738022, "count": 10, "is_parallel": true, "self": 0.003054853528738022 } } }, "UnityEnvironment.step": { "total": 0.05857975780963898, "count": 1, "is_parallel": true, "self": 0.0009105689823627472, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000627957284450531, "count": 1, "is_parallel": true, "self": 0.000627957284450531 }, "communicator.exchange": { "total": 0.05426255241036415, "count": 1, "is_parallel": true, "self": 0.05426255241036415 }, "steps_from_proto": { "total": 0.002778679132461548, "count": 1, "is_parallel": true, "self": 0.000672709196805954, "children": { "_process_rank_one_or_two_observation": { "total": 0.002105969935655594, "count": 10, "is_parallel": true, "self": 0.002105969935655594 } } } } } } }, "UnityEnvironment.step": { "total": 366.71843395382166, "count": 18202, "is_parallel": true, "self": 15.889967773109674, "children": { "UnityEnvironment._generate_step_input": { "total": 8.847616668790579, "count": 18202, "is_parallel": true, "self": 8.847616668790579 }, "communicator.exchange": { "total": 295.01977460831404, "count": 18202, "is_parallel": true, "self": 295.01977460831404 }, "steps_from_proto": { "total": 46.96107490360737, "count": 18202, "is_parallel": true, "self": 10.344161704182625, "children": { "_process_rank_one_or_two_observation": { "total": 36.616913199424744, "count": 182020, "is_parallel": true, "self": 36.616913199424744 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019016116857528687, "count": 1, "self": 0.00019016116857528687, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 560.2121567800641, "count": 244995, "is_parallel": true, "self": 3.976197514683008, "children": { "process_trajectory": { "total": 326.1053060814738, "count": 244995, "is_parallel": true, "self": 325.2289860062301, "children": { "RLTrainer._checkpoint": { "total": 0.8763200752437115, "count": 4, "is_parallel": true, "self": 0.8763200752437115 } } }, "_update_policy": { "total": 230.13065318390727, "count": 90, "is_parallel": true, "self": 29.199153769761324, "children": { "TorchPPOOptimizer.update": { "total": 200.93149941414595, "count": 4587, "is_parallel": true, "self": 200.93149941414595 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07130062952637672, "count": 1, "self": 0.0007156208157539368, "children": { "RLTrainer._checkpoint": { "total": 0.07058500871062279, "count": 1, "self": 0.07058500871062279 } } } } } } }