{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.106321334838867, "min": 2.106321334838867, "max": 2.8895676136016846, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 20829.412109375, "min": 20829.412109375, "max": 29560.27734375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9984.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9984.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 5.986812114715576, "min": 0.15450522303581238, "max": 5.986812114715576, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2071.43701171875, "min": 53.30430221557617, "max": 2112.815185546875, "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": 0.032693109060346615, "min": 0.022358968895180926, "max": 0.037340058974223204, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.13077243624138646, "min": 0.0908888581955883, "max": 0.1730511592249968, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24121169311304888, "min": 0.06690123033088942, "max": 0.2700536241134008, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9648467724521955, "min": 0.2676049213235577, "max": 1.350268120567004, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.694097306000002e-06, "min": 2.694097306000002e-06, "max": 9.7294002706e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0776389224000008e-05, "min": 1.0776389224000008e-05, "max": 0.00046172003828000004, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102694, "min": 0.102694, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.410776, "min": 0.410776, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 11.340909090909092, "min": 2.1818181818181817, "max": 11.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 499.0, "min": 96.0, "max": 643.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 11.340909090909092, "min": 2.1818181818181817, "max": 11.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 499.0, "min": 96.0, "max": 643.0, "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": "1690033686", "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", "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": "1690034131" }, "total": 444.8723131789999, "count": 1, "self": 0.43516572499993345, "children": { "run_training.setup": { "total": 0.0540771500000119, "count": 1, "self": 0.0540771500000119 }, "TrainerController.start_learning": { "total": 444.38307030399994, "count": 1, "self": 0.5364654820109536, "children": { "TrainerController._reset_env": { "total": 5.3830870919999825, "count": 1, "self": 5.3830870919999825 }, "TrainerController.advance": { "total": 438.32524669398913, "count": 18201, "self": 0.258751011968684, "children": { "env_step": { "total": 438.06649568202045, "count": 18201, "self": 304.84631349803954, "children": { "SubprocessEnvManager._take_step": { "total": 132.95581780198438, "count": 18201, "self": 1.678208455977483, "children": { "TorchPolicy.evaluate": { "total": 131.2776093460069, "count": 18201, "self": 131.2776093460069 } } }, "workers": { "total": 0.2643643819965291, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 443.02296877100093, "count": 18201, "is_parallel": true, "self": 205.01364398200496, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002250892000006388, "count": 1, "is_parallel": true, "self": 0.0007719470000893125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014789449999170756, "count": 10, "is_parallel": true, "self": 0.0014789449999170756 } } }, "UnityEnvironment.step": { "total": 0.048344817000042895, "count": 1, "is_parallel": true, "self": 0.00040699500016216916, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003612729999531439, "count": 1, "is_parallel": true, "self": 0.0003612729999531439 }, "communicator.exchange": { "total": 0.04631800699996802, "count": 1, "is_parallel": true, "self": 0.04631800699996802 }, "steps_from_proto": { "total": 0.0012585419999595615, "count": 1, "is_parallel": true, "self": 0.00025813500008098345, "children": { "_process_rank_one_or_two_observation": { "total": 0.001000406999878578, "count": 10, "is_parallel": true, "self": 0.001000406999878578 } } } } } } }, "UnityEnvironment.step": { "total": 238.00932478899597, "count": 18200, "is_parallel": true, "self": 10.529385611990506, "children": { "UnityEnvironment._generate_step_input": { "total": 5.181530321001674, "count": 18200, "is_parallel": true, "self": 5.181530321001674 }, "communicator.exchange": { "total": 187.92970271700926, "count": 18200, "is_parallel": true, "self": 187.92970271700926 }, "steps_from_proto": { "total": 34.368706138994526, "count": 18200, "is_parallel": true, "self": 6.195796961001065, "children": { "_process_rank_one_or_two_observation": { "total": 28.17290917799346, "count": 182000, "is_parallel": true, "self": 28.17290917799346 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011239299988119456, "count": 1, "self": 0.00011239299988119456, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 433.89626659110604, "count": 487725, "is_parallel": true, "self": 11.476844285080915, "children": { "process_trajectory": { "total": 301.11649805902584, "count": 487725, "is_parallel": true, "self": 299.9978231660257, "children": { "RLTrainer._checkpoint": { "total": 1.1186748930001613, "count": 4, "is_parallel": true, "self": 1.1186748930001613 } } }, "_update_policy": { "total": 121.30292424699928, "count": 90, "is_parallel": true, "self": 73.31672924299937, "children": { "TorchPPOOptimizer.update": { "total": 47.98619500399991, "count": 1080, "is_parallel": true, "self": 47.98619500399991 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13815864299999703, "count": 1, "self": 0.0008055169998897327, "children": { "RLTrainer._checkpoint": { "total": 0.1373531260001073, "count": 1, "self": 0.1373531260001073 } } } } } } }