{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9691912531852722, "min": 0.9691912531852722, "max": 2.8547604084014893, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9243.1767578125, "min": 9243.1767578125, "max": 29235.6015625, "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": 13.400653839111328, "min": 0.39931046962738037, "max": 13.51445198059082, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2613.12744140625, "min": 77.46623229980469, "max": 2756.456787109375, "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": 0.06943172063721945, "min": 0.06553791098376678, "max": 0.07353814042995081, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2777268825488778, "min": 0.2621516439350671, "max": 0.3676907021497541, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1770546653910595, "min": 0.12274705784682952, "max": 0.28022431575638407, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.708218661564238, "min": 0.49098823138731806, "max": 1.315684741297189, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.0013851600382799997, "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": 0.9617200000000001, "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": 26.295454545454547, "min": 4.0227272727272725, "max": 26.490909090909092, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1157.0, "min": 177.0, "max": 1457.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.295454545454547, "min": 4.0227272727272725, "max": 26.490909090909092, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1157.0, "min": 177.0, "max": 1457.0, "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": "1673370163", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673370779" }, "total": 616.9305473180002, "count": 1, "self": 0.38820713300015086, "children": { "run_training.setup": { "total": 0.10746501300013733, "count": 1, "self": 0.10746501300013733 }, "TrainerController.start_learning": { "total": 616.4348751719999, "count": 1, "self": 0.5078972250021252, "children": { "TrainerController._reset_env": { "total": 8.517950889000076, "count": 1, "self": 8.517950889000076 }, "TrainerController.advance": { "total": 607.2827824889982, "count": 18203, "self": 0.25616611001623824, "children": { "env_step": { "total": 607.026616378982, "count": 18203, "self": 460.06393688195067, "children": { "SubprocessEnvManager._take_step": { "total": 146.69948821101843, "count": 18203, "self": 1.3573593030143911, "children": { "TorchPolicy.evaluate": { "total": 145.34212890800404, "count": 18203, "self": 32.66103243599082, "children": { "TorchPolicy.sample_actions": { "total": 112.68109647201322, "count": 18203, "self": 112.68109647201322 } } } } }, "workers": { "total": 0.26319128601289776, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 615.1903098529897, "count": 18203, "is_parallel": true, "self": 397.2321358399861, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005542058999935762, "count": 1, "is_parallel": true, "self": 0.0031921669994972035, "children": { "_process_rank_one_or_two_observation": { "total": 0.002349892000438558, "count": 10, "is_parallel": true, "self": 0.002349892000438558 } } }, "UnityEnvironment.step": { "total": 0.032841696999867054, "count": 1, "is_parallel": true, "self": 0.0005305549998411152, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037286199994923663, "count": 1, "is_parallel": true, "self": 0.00037286199994923663 }, "communicator.exchange": { "total": 0.03012855999986641, "count": 1, "is_parallel": true, "self": 0.03012855999986641 }, "steps_from_proto": { "total": 0.0018097200002102909, "count": 1, "is_parallel": true, "self": 0.0004144150002503011, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013953049999599898, "count": 10, "is_parallel": true, "self": 0.0013953049999599898 } } } } } } }, "UnityEnvironment.step": { "total": 217.9581740130036, "count": 18202, "is_parallel": true, "self": 8.362239242990427, "children": { "UnityEnvironment._generate_step_input": { "total": 4.991336620012362, "count": 18202, "is_parallel": true, "self": 4.991336620012362 }, "communicator.exchange": { "total": 172.47982819102117, "count": 18202, "is_parallel": true, "self": 172.47982819102117 }, "steps_from_proto": { "total": 32.12476995897964, "count": 18202, "is_parallel": true, "self": 6.565998277023255, "children": { "_process_rank_one_or_two_observation": { "total": 25.558771681956387, "count": 182020, "is_parallel": true, "self": 25.558771681956387 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.52079998467525e-05, "count": 1, "self": 4.52079998467525e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 604.3309083509896, "count": 331963, "is_parallel": true, "self": 9.038655579061924, "children": { "process_trajectory": { "total": 238.02562971292696, "count": 331963, "is_parallel": true, "self": 237.16832442892724, "children": { "RLTrainer._checkpoint": { "total": 0.8573052839997217, "count": 4, "is_parallel": true, "self": 0.8573052839997217 } } }, "_update_policy": { "total": 357.2666230590007, "count": 90, "is_parallel": true, "self": 139.13507826699924, "children": { "TorchPPOOptimizer.update": { "total": 218.13154479200148, "count": 15290, "is_parallel": true, "self": 218.13154479200148 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12619936099963525, "count": 1, "self": 0.0010316429998056265, "children": { "RLTrainer._checkpoint": { "total": 0.12516771799982962, "count": 1, "self": 0.12516771799982962 } } } } } } }