{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0965946912765503, "min": 1.0965946912765503, "max": 2.871347188949585, "count": 15 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11326.7265625, "min": 10627.7333984375, "max": 29531.8046875, "count": 15 }, "SnowballTarget.Step.mean": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Step.sum": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.291963577270508, "min": 0.4709761440753937, "max": 12.291963577270508, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.8525390625, "min": 91.36936950683594, "max": 2519.8525390625, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07247265397077973, "min": 0.06021540737300015, "max": 0.0744482664592272, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.36236326985389866, "min": 0.2512494323914414, "max": 0.36787161426949677, "count": 15 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22786991952681074, "min": 0.12675959277925467, "max": 0.3243674635887146, "count": 15 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1393495976340537, "min": 0.5070383711170187, "max": 1.4721975349912455, "count": 15 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.776096741333334e-06, "min": 9.776096741333334e-06, "max": 0.000289176003608, "count": 15 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.888048370666667e-05, "min": 4.888048370666667e-05, "max": 0.0013468800510399999, "count": 15 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10325866666666668, "min": 0.10325866666666668, "max": 0.19639199999999998, "count": 15 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5162933333333334, "min": 0.43943466666666664, "max": 0.94896, "count": 15 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00017260746666666673, "min": 0.00017260746666666673, "max": 0.004819960799999999, "count": 15 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0008630373333333337, "min": 0.0008630373333333337, "max": 0.022453104, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.727272727272727, "min": 3.4545454545454546, "max": 24.727272727272727, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1360.0, "min": 152.0, "max": 1360.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.727272727272727, "min": 3.4545454545454546, "max": 24.727272727272727, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1360.0, "min": 152.0, "max": 1360.0, "count": 15 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691757505", "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": "1691757866" }, "total": 361.466566736, "count": 1, "self": 0.4329747970001563, "children": { "run_training.setup": { "total": 0.07415404899995792, "count": 1, "self": 0.07415404899995792 }, "TrainerController.start_learning": { "total": 360.9594378899999, "count": 1, "self": 0.42937892200473016, "children": { "TrainerController._reset_env": { "total": 4.600265164999996, "count": 1, "self": 4.600265164999996 }, "TrainerController.advance": { "total": 355.78926058699517, "count": 13678, "self": 0.20644044798427785, "children": { "env_step": { "total": 355.5828201390109, "count": 13678, "self": 259.2204320310076, "children": { "SubprocessEnvManager._take_step": { "total": 96.14532543999837, "count": 13678, "self": 1.2861616690125857, "children": { "TorchPolicy.evaluate": { "total": 94.85916377098579, "count": 13678, "self": 94.85916377098579 } } }, "workers": { "total": 0.21706266800492813, "count": 13678, "self": 0.0, "children": { "worker_root": { "total": 359.76862194597936, "count": 13678, "is_parallel": true, "self": 171.8938366669679, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006921400999999605, "count": 1, "is_parallel": true, "self": 0.00434498499998881, "children": { "_process_rank_one_or_two_observation": { "total": 0.002576416000010795, "count": 10, "is_parallel": true, "self": 0.002576416000010795 } } }, "UnityEnvironment.step": { "total": 0.045008891999941625, "count": 1, "is_parallel": true, "self": 0.0006204999998544736, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003299400000287278, "count": 1, "is_parallel": true, "self": 0.0003299400000287278 }, "communicator.exchange": { "total": 0.041857010000057926, "count": 1, "is_parallel": true, "self": 0.041857010000057926 }, "steps_from_proto": { "total": 0.0022014420000004975, "count": 1, "is_parallel": true, "self": 0.00039154800026608427, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018098939997344132, "count": 10, "is_parallel": true, "self": 0.0018098939997344132 } } } } } } }, "UnityEnvironment.step": { "total": 187.87478527901146, "count": 13677, "is_parallel": true, "self": 8.057016022008611, "children": { "UnityEnvironment._generate_step_input": { "total": 3.9179228649867355, "count": 13677, "is_parallel": true, "self": 3.9179228649867355 }, "communicator.exchange": { "total": 148.60489038400146, "count": 13677, "is_parallel": true, "self": 148.60489038400146 }, "steps_from_proto": { "total": 27.29495600801465, "count": 13677, "is_parallel": true, "self": 5.0210302379882705, "children": { "_process_rank_one_or_two_observation": { "total": 22.27392577002638, "count": 136770, "is_parallel": true, "self": 22.27392577002638 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001385240000217891, "count": 1, "self": 0.0001385240000217891, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 353.14637424408545, "count": 320503, "is_parallel": true, "self": 7.254311375010275, "children": { "process_trajectory": { "total": 192.7869828540753, "count": 320503, "is_parallel": true, "self": 191.71337951007524, "children": { "RLTrainer._checkpoint": { "total": 1.0736033440000483, "count": 3, "is_parallel": true, "self": 1.0736033440000483 } } }, "_update_policy": { "total": 153.10508001499988, "count": 68, "is_parallel": true, "self": 58.260012834002055, "children": { "TorchPPOOptimizer.update": { "total": 94.84506718099783, "count": 3465, "is_parallel": true, "self": 94.84506718099783 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14039469199997257, "count": 1, "self": 0.0008616939999228634, "children": { "RLTrainer._checkpoint": { "total": 0.1395329980000497, "count": 1, "self": 0.1395329980000497 } } } } } } }