{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9882222414016724, "min": 0.9882222414016724, "max": 2.8491950035095215, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9489.8984375, "min": 9489.8984375, "max": 29178.60546875, "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": 12.657785415649414, "min": 0.3612315058708191, "max": 12.657785415649414, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2468.26806640625, "min": 70.07891082763672, "max": 2565.384521484375, "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": 0.07013915791621378, "min": 0.06461056044859373, "max": 0.07207371729960228, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2805566316648551, "min": 0.2651873705596218, "max": 0.3603685864980114, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.208304752540939, "min": 0.12503924420989102, "max": 0.29443430211029803, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.833219010163756, "min": 0.5001569768395641, "max": 1.47217151055149, "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": 25.25, "min": 3.522727272727273, "max": 25.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 155.0, "max": 1364.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.522727272727273, "max": 25.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 155.0, "max": 1364.0, "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": "1694421455", "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=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": "1694421986" }, "total": 530.998513606, "count": 1, "self": 0.5464392849999058, "children": { "run_training.setup": { "total": 0.04316021900001488, "count": 1, "self": 0.04316021900001488 }, "TrainerController.start_learning": { "total": 530.408914102, "count": 1, "self": 0.6834757209982172, "children": { "TrainerController._reset_env": { "total": 4.164128592999987, "count": 1, "self": 4.164128592999987 }, "TrainerController.advance": { "total": 525.3167177290019, "count": 18210, "self": 0.349762609988602, "children": { "env_step": { "total": 524.9669551190133, "count": 18210, "self": 383.38298967301057, "children": { "SubprocessEnvManager._take_step": { "total": 141.24886340500268, "count": 18210, "self": 2.1845318640035885, "children": { "TorchPolicy.evaluate": { "total": 139.0643315409991, "count": 18210, "self": 139.0643315409991 } } }, "workers": { "total": 0.3351020410000274, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 528.6075142489893, "count": 18210, "is_parallel": true, "self": 245.8414238429889, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005850988000020152, "count": 1, "is_parallel": true, "self": 0.004060644999981378, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017903430000387743, "count": 10, "is_parallel": true, "self": 0.0017903430000387743 } } }, "UnityEnvironment.step": { "total": 0.051403087000039704, "count": 1, "is_parallel": true, "self": 0.0006685320001338368, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037423699995997595, "count": 1, "is_parallel": true, "self": 0.00037423699995997595 }, "communicator.exchange": { "total": 0.04664906699997573, "count": 1, "is_parallel": true, "self": 0.04664906699997573 }, "steps_from_proto": { "total": 0.0037112509999701615, "count": 1, "is_parallel": true, "self": 0.0004533350000315295, "children": { "_process_rank_one_or_two_observation": { "total": 0.003257915999938632, "count": 10, "is_parallel": true, "self": 0.003257915999938632 } } } } } } }, "UnityEnvironment.step": { "total": 282.76609040600044, "count": 18209, "is_parallel": true, "self": 11.738403656007733, "children": { "UnityEnvironment._generate_step_input": { "total": 6.045633294997231, "count": 18209, "is_parallel": true, "self": 6.045633294997231 }, "communicator.exchange": { "total": 222.85789080599375, "count": 18209, "is_parallel": true, "self": 222.85789080599375 }, "steps_from_proto": { "total": 42.12416264900173, "count": 18209, "is_parallel": true, "self": 8.002488693017824, "children": { "_process_rank_one_or_two_observation": { "total": 34.12167395598391, "count": 182090, "is_parallel": true, "self": 34.12167395598391 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013454599991291616, "count": 1, "self": 0.00013454599991291616, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 520.8666871270068, "count": 487277, "is_parallel": true, "self": 12.10536548404724, "children": { "process_trajectory": { "total": 289.02255846195965, "count": 487277, "is_parallel": true, "self": 286.9108961989597, "children": { "RLTrainer._checkpoint": { "total": 2.111662262999971, "count": 4, "is_parallel": true, "self": 2.111662262999971 } } }, "_update_policy": { "total": 219.7387631809999, "count": 90, "is_parallel": true, "self": 84.39323850199935, "children": { "TorchPPOOptimizer.update": { "total": 135.34552467900056, "count": 4587, "is_parallel": true, "self": 135.34552467900056 } } } } } } } } }, "TrainerController._save_models": { "total": 0.24445751300004304, "count": 1, "self": 0.0012442470000451067, "children": { "RLTrainer._checkpoint": { "total": 0.24321326599999793, "count": 1, "self": 0.24321326599999793 } } } } } } }