{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8960713744163513, "min": 0.8949620127677917, "max": 2.8713607788085938, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8585.259765625, "min": 8585.259765625, "max": 29531.9453125, "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": 12.795312881469727, "min": 0.3766804337501526, "max": 12.795312881469727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2495.0859375, "min": 73.07600402832031, "max": 2592.4775390625, "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": 0.06441009030922763, "min": 0.06441009030922763, "max": 0.07703820894034032, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25764036123691053, "min": 0.25764036123691053, "max": 0.38519104470170157, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19399183897265032, "min": 0.12134793356823388, "max": 0.2927957919882793, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7759673558906013, "min": 0.4853917342729355, "max": 1.4639789599413966, "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": 25.318181818181817, "min": 3.5681818181818183, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1114.0, "min": 157.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.318181818181817, "min": 3.5681818181818183, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1114.0, "min": 157.0, "max": 1386.0, "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": "1700213867", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700214535" }, "total": 668.125257329, "count": 1, "self": 0.5373887519999698, "children": { "run_training.setup": { "total": 0.057306616000005306, "count": 1, "self": 0.057306616000005306 }, "TrainerController.start_learning": { "total": 667.530561961, "count": 1, "self": 0.909551870981204, "children": { "TrainerController._reset_env": { "total": 1.2729417499999727, "count": 1, "self": 1.2729417499999727 }, "TrainerController.advance": { "total": 665.249798838019, "count": 18203, "self": 0.4716272300128139, "children": { "env_step": { "total": 664.7781716080062, "count": 18203, "self": 526.6191069429877, "children": { "SubprocessEnvManager._take_step": { "total": 137.7183071200119, "count": 18203, "self": 2.68766987602487, "children": { "TorchPolicy.evaluate": { "total": 135.03063724398703, "count": 18203, "self": 135.03063724398703 } } }, "workers": { "total": 0.4407575450065906, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 664.8972165579979, "count": 18203, "is_parallel": true, "self": 306.0108396689984, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002385325000091143, "count": 1, "is_parallel": true, "self": 0.0007248729999673742, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016604520001237688, "count": 10, "is_parallel": true, "self": 0.0016604520001237688 } } }, "UnityEnvironment.step": { "total": 0.06406840700003613, "count": 1, "is_parallel": true, "self": 0.0007396140000537343, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005326780000132203, "count": 1, "is_parallel": true, "self": 0.0005326780000132203 }, "communicator.exchange": { "total": 0.060427391999951396, "count": 1, "is_parallel": true, "self": 0.060427391999951396 }, "steps_from_proto": { "total": 0.0023687230000177806, "count": 1, "is_parallel": true, "self": 0.00044277799997871625, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019259450000390643, "count": 10, "is_parallel": true, "self": 0.0019259450000390643 } } } } } } }, "UnityEnvironment.step": { "total": 358.8863768889995, "count": 18202, "is_parallel": true, "self": 15.30407611797773, "children": { "UnityEnvironment._generate_step_input": { "total": 7.812224881031284, "count": 18202, "is_parallel": true, "self": 7.812224881031284 }, "communicator.exchange": { "total": 286.00907331899975, "count": 18202, "is_parallel": true, "self": 286.00907331899975 }, "steps_from_proto": { "total": 49.76100257099074, "count": 18202, "is_parallel": true, "self": 10.03324021204537, "children": { "_process_rank_one_or_two_observation": { "total": 39.72776235894537, "count": 182020, "is_parallel": true, "self": 39.72776235894537 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.149699985755433e-05, "count": 1, "self": 9.149699985755433e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 658.1599903669684, "count": 695969, "is_parallel": true, "self": 18.15263410012392, "children": { "process_trajectory": { "total": 354.0358871278445, "count": 695969, "is_parallel": true, "self": 353.4998522998442, "children": { "RLTrainer._checkpoint": { "total": 0.5360348280003109, "count": 4, "is_parallel": true, "self": 0.5360348280003109 } } }, "_update_policy": { "total": 285.97146913899996, "count": 90, "is_parallel": true, "self": 89.78553824600579, "children": { "TorchPPOOptimizer.update": { "total": 196.18593089299418, "count": 4587, "is_parallel": true, "self": 196.18593089299418 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09817800499990881, "count": 1, "self": 0.0012312719998135435, "children": { "RLTrainer._checkpoint": { "total": 0.09694673300009526, "count": 1, "self": 0.09694673300009526 } } } } } } }