{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.0231661796569824, "min": 1.9793037176132202, "max": 2.8879189491271973, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10303.9853515625, "min": 9281.365234375, "max": 15057.609375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 4976.0, "max": 99960.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 4976.0, "max": 99960.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 6.6765570640563965, "min": 0.13282358646392822, "max": 6.6765570640563965, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 647.6260375976562, "min": 12.88388729095459, "max": 706.9190063476562, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 4378.0, "min": 4378.0, "max": 6567.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.05241448506785673, "min": 0.03406329707892534, "max": 0.052879361125330135, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.10482897013571346, "min": 0.06812659415785068, "max": 0.1522821356144656, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24856809930255014, "min": 0.0926407778946062, "max": 0.293659967266851, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4971361986051003, "min": 0.1852815557892124, "max": 0.8809799018005531, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.564097812000003e-06, "min": 6.564097812000003e-06, "max": 0.000290364003212, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.3128195624000006e-05, "min": 1.3128195624000006e-05, "max": 0.0007423920525360001, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102188, "min": 0.102188, "max": 0.196788, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.204376, "min": 0.204376, "max": 0.5474640000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00011918120000000006, "min": 0.00011918120000000006, "max": 0.0048397212, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00023836240000000013, "min": 0.00023836240000000013, "max": 0.012378453600000002, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 12.727272727272727, "min": 2.6818181818181817, "max": 14.424242424242424, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 280.0, "min": 59.0, "max": 476.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 12.727272727272727, "min": 2.6818181818181817, "max": 14.424242424242424, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 280.0, "min": 59.0, "max": 476.0, "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": "1681497524", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1681497745" }, "total": 220.77448978399997, "count": 1, "self": 0.43183463800005484, "children": { "run_training.setup": { "total": 0.18392681699998548, "count": 1, "self": 0.18392681699998548 }, "TrainerController.start_learning": { "total": 220.15872832899993, "count": 1, "self": 0.29805306899908146, "children": { "TrainerController._reset_env": { "total": 4.440296907000004, "count": 1, "self": 4.440296907000004 }, "TrainerController.advance": { "total": 215.2921510100008, "count": 9136, "self": 0.13523331099514735, "children": { "env_step": { "total": 215.15691769900565, "count": 9136, "self": 152.31179755100237, "children": { "SubprocessEnvManager._take_step": { "total": 62.714598094003236, "count": 9136, "self": 0.8679112110056622, "children": { "TorchPolicy.evaluate": { "total": 61.846686882997574, "count": 9136, "self": 61.846686882997574 } } }, "workers": { "total": 0.13052205400003913, "count": 9136, "self": 0.0, "children": { "worker_root": { "total": 219.37788660600177, "count": 9136, "is_parallel": true, "self": 97.7634387640008, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00578765900002054, "count": 1, "is_parallel": true, "self": 0.003548502000114695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022391569999058447, "count": 10, "is_parallel": true, "self": 0.0022391569999058447 } } }, "UnityEnvironment.step": { "total": 0.036692402999960905, "count": 1, "is_parallel": true, "self": 0.0004881329999761874, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038607800001955184, "count": 1, "is_parallel": true, "self": 0.00038607800001955184 }, "communicator.exchange": { "total": 0.03428974799999196, "count": 1, "is_parallel": true, "self": 0.03428974799999196 }, "steps_from_proto": { "total": 0.0015284439999732058, "count": 1, "is_parallel": true, "self": 0.00034613799999760886, "children": { "_process_rank_one_or_two_observation": { "total": 0.001182305999975597, "count": 10, "is_parallel": true, "self": 0.001182305999975597 } } } } } } }, "UnityEnvironment.step": { "total": 121.61444784200097, "count": 9135, "is_parallel": true, "self": 4.954297335999456, "children": { "UnityEnvironment._generate_step_input": { "total": 2.6936184999979105, "count": 9135, "is_parallel": true, "self": 2.6936184999979105 }, "communicator.exchange": { "total": 98.27243934799776, "count": 9135, "is_parallel": true, "self": 98.27243934799776 }, "steps_from_proto": { "total": 15.694092658005843, "count": 9135, "is_parallel": true, "self": 3.1229783899958647, "children": { "_process_rank_one_or_two_observation": { "total": 12.571114268009978, "count": 91350, "is_parallel": true, "self": 12.571114268009978 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003327939999735463, "count": 1, "self": 0.0003327939999735463, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 213.54254517599088, "count": 211483, "is_parallel": true, "self": 5.145933059987783, "children": { "process_trajectory": { "total": 126.5157001790032, "count": 211483, "is_parallel": true, "self": 125.31430665400313, "children": { "RLTrainer._checkpoint": { "total": 1.2013935250000713, "count": 4, "is_parallel": true, "self": 1.2013935250000713 } } }, "_update_policy": { "total": 81.8809119369999, "count": 45, "is_parallel": true, "self": 38.79543692800172, "children": { "TorchPPOOptimizer.update": { "total": 43.08547500899817, "count": 1080, "is_parallel": true, "self": 43.08547500899817 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12789454900007513, "count": 1, "self": 0.0009009480000941039, "children": { "RLTrainer._checkpoint": { "total": 0.12699360099998103, "count": 1, "self": 0.12699360099998103 } } } } } } }