{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1701154708862305, "min": 1.1701154708862305, "max": 2.856102228164673, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11223.748046875, "min": 11223.748046875, "max": 29343.59375, "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": 12.518049240112305, "min": 0.31733497977256775, "max": 12.518049240112305, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2441.01953125, "min": 61.56298828125, "max": 2537.745361328125, "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": 0.0637488459728689, "min": 0.06335116902982027, "max": 0.07813777631442873, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2549953838914756, "min": 0.2534046761192811, "max": 0.3586449908660357, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.223179226923807, "min": 0.137109606303092, "max": 0.2793384957693371, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.892716907695228, "min": 0.548438425212368, "max": 1.3706489830624824, "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": 25.068181818181817, "min": 3.6363636363636362, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1103.0, "min": 160.0, "max": 1352.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.068181818181817, "min": 3.6363636363636362, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1103.0, "min": 160.0, "max": 1352.0, "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": "1689866865", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1689867447" }, "total": 581.858019111, "count": 1, "self": 0.7497220610002842, "children": { "run_training.setup": { "total": 0.04641030699986004, "count": 1, "self": 0.04641030699986004 }, "TrainerController.start_learning": { "total": 581.0618867429998, "count": 1, "self": 0.658340916981615, "children": { "TrainerController._reset_env": { "total": 7.094885479999903, "count": 1, "self": 7.094885479999903 }, "TrainerController.advance": { "total": 573.0738437620189, "count": 18223, "self": 0.2935796360484346, "children": { "env_step": { "total": 572.7802641259705, "count": 18223, "self": 454.6927671980361, "children": { "SubprocessEnvManager._take_step": { "total": 117.76998982794703, "count": 18223, "self": 2.8711500310428164, "children": { "TorchPolicy.evaluate": { "total": 114.89883979690421, "count": 18223, "self": 114.89883979690421 } } }, "workers": { "total": 0.3175070999873242, "count": 18223, "self": 0.0, "children": { "worker_root": { "total": 579.2634633479879, "count": 18223, "is_parallel": true, "self": 303.8838550390142, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00575366800012489, "count": 1, "is_parallel": true, "self": 0.003399357000944292, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023543109991805977, "count": 10, "is_parallel": true, "self": 0.0023543109991805977 } } }, "UnityEnvironment.step": { "total": 0.06292708299997685, "count": 1, "is_parallel": true, "self": 0.0006869440007903904, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003711199997269432, "count": 1, "is_parallel": true, "self": 0.0003711199997269432 }, "communicator.exchange": { "total": 0.059364014999573556, "count": 1, "is_parallel": true, "self": 0.059364014999573556 }, "steps_from_proto": { "total": 0.0025050039998859575, "count": 1, "is_parallel": true, "self": 0.0006068199991204892, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018981840007654682, "count": 10, "is_parallel": true, "self": 0.0018981840007654682 } } } } } } }, "UnityEnvironment.step": { "total": 275.37960830897373, "count": 18222, "is_parallel": true, "self": 11.163732661914764, "children": { "UnityEnvironment._generate_step_input": { "total": 5.3825570879953375, "count": 18222, "is_parallel": true, "self": 5.3825570879953375 }, "communicator.exchange": { "total": 222.62376235901684, "count": 18222, "is_parallel": true, "self": 222.62376235901684 }, "steps_from_proto": { "total": 36.20955620004679, "count": 18222, "is_parallel": true, "self": 6.430131927049388, "children": { "_process_rank_one_or_two_observation": { "total": 29.779424272997403, "count": 182220, "is_parallel": true, "self": 29.779424272997403 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013027899967710255, "count": 1, "self": 0.00013027899967710255, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 567.67908773014, "count": 695301, "is_parallel": true, "self": 13.68601575223147, "children": { "process_trajectory": { "total": 292.16261992190766, "count": 695301, "is_parallel": true, "self": 289.14387117190836, "children": { "RLTrainer._checkpoint": { "total": 3.018748749999304, "count": 4, "is_parallel": true, "self": 3.018748749999304 } } }, "_update_policy": { "total": 261.8304520560009, "count": 90, "is_parallel": true, "self": 175.25852496901007, "children": { "TorchPPOOptimizer.update": { "total": 86.57192708699085, "count": 4584, "is_parallel": true, "self": 86.57192708699085 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23468630499974097, "count": 1, "self": 0.0010699399995246495, "children": { "RLTrainer._checkpoint": { "total": 0.23361636500021632, "count": 1, "self": 0.23361636500021632 } } } } } } }