{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6111616492271423, "min": 0.6020801663398743, "max": 1.006426215171814, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5922.767578125, "min": 5922.767578125, "max": 10306.810546875, "count": 30 }, "SnowballTarget.Step.mean": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.718453407287598, "min": 11.935287475585938, "max": 13.718453407287598, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2798.564453125, "min": 2291.5751953125, "max": 2798.564453125, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07402257264737844, "min": 0.05955052187961758, "max": 0.07521595742839375, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3701128632368922, "min": 0.253847525737536, "max": 0.3701128632368922, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16425055075509876, "min": 0.16425055075509876, "max": 0.21396342672261537, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8212527537754938, "min": 0.6668591440892687, "max": 1.053250604108268, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.1056989647999945e-06, "min": 3.1056989647999945e-06, "max": 0.00017668564110480002, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5528494823999972e-05, "min": 1.5528494823999972e-05, "max": 0.000853728215424, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10103520000000002, "min": 0.10103520000000002, "max": 0.15889520000000001, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5051760000000001, "min": 0.4120608, "max": 0.7845760000000002, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.165647999999992e-05, "min": 6.165647999999992e-05, "max": 0.002948870480000001, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003082823999999996, "min": 0.0003082823999999996, "max": 0.0142503424, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.854545454545455, "min": 23.59090909090909, "max": 27.363636363636363, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1477.0, "min": 1038.0, "max": 1477.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.854545454545455, "min": 23.59090909090909, "max": 27.363636363636363, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1477.0, "min": 1038.0, "max": 1477.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682136271", "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 --resume --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": "1682137012" }, "total": 741.122602874, "count": 1, "self": 0.4362290189999385, "children": { "run_training.setup": { "total": 0.1091867390000516, "count": 1, "self": 0.1091867390000516 }, "TrainerController.start_learning": { "total": 740.577187116, "count": 1, "self": 0.8936099449829271, "children": { "TrainerController._reset_env": { "total": 3.6925066240000888, "count": 1, "self": 3.6925066240000888 }, "TrainerController.advance": { "total": 735.8311361570172, "count": 27279, "self": 0.43456922200311965, "children": { "env_step": { "total": 735.3965669350141, "count": 27279, "self": 537.5170754270223, "children": { "SubprocessEnvManager._take_step": { "total": 197.42547882999975, "count": 27279, "self": 2.695097105008699, "children": { "TorchPolicy.evaluate": { "total": 194.73038172499105, "count": 27279, "self": 194.73038172499105 } } }, "workers": { "total": 0.45401267799206835, "count": 27279, "self": 0.0, "children": { "worker_root": { "total": 738.1303619209982, "count": 27279, "is_parallel": true, "self": 339.3599613709903, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020002449998628435, "count": 1, "is_parallel": true, "self": 0.0005929679996370396, "children": { "_process_rank_one_or_two_observation": { "total": 0.001407277000225804, "count": 10, "is_parallel": true, "self": 0.001407277000225804 } } }, "UnityEnvironment.step": { "total": 0.043185691999951814, "count": 1, "is_parallel": true, "self": 0.0005953960001079395, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004180319999704807, "count": 1, "is_parallel": true, "self": 0.0004180319999704807 }, "communicator.exchange": { "total": 0.040094974999874466, "count": 1, "is_parallel": true, "self": 0.040094974999874466 }, "steps_from_proto": { "total": 0.0020772889999989275, "count": 1, "is_parallel": true, "self": 0.00043218099972364143, "children": { "_process_rank_one_or_two_observation": { "total": 0.001645108000275286, "count": 10, "is_parallel": true, "self": 0.001645108000275286 } } } } } } }, "UnityEnvironment.step": { "total": 398.77040055000793, "count": 27278, "is_parallel": true, "self": 15.804879973953803, "children": { "UnityEnvironment._generate_step_input": { "total": 9.001173710992816, "count": 27278, "is_parallel": true, "self": 9.001173710992816 }, "communicator.exchange": { "total": 320.3141387400333, "count": 27278, "is_parallel": true, "self": 320.3141387400333 }, "steps_from_proto": { "total": 53.65020812502803, "count": 27278, "is_parallel": true, "self": 10.850477102992045, "children": { "_process_rank_one_or_two_observation": { "total": 42.799731022035985, "count": 272780, "is_parallel": true, "self": 42.799731022035985 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016255799982900498, "count": 1, "self": 0.00016255799982900498, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 729.8327008439385, "count": 658923, "is_parallel": true, "self": 17.097474611860434, "children": { "process_trajectory": { "total": 404.40310967007713, "count": 658923, "is_parallel": true, "self": 403.2105333320769, "children": { "RLTrainer._checkpoint": { "total": 1.1925763380002081, "count": 6, "is_parallel": true, "self": 1.1925763380002081 } } }, "_update_policy": { "total": 308.3321165620009, "count": 136, "is_parallel": true, "self": 114.48492151399091, "children": { "TorchPPOOptimizer.update": { "total": 193.84719504801, "count": 6933, "is_parallel": true, "self": 193.84719504801 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15977183199993306, "count": 1, "self": 0.001171401000192418, "children": { "RLTrainer._checkpoint": { "total": 0.15860043099974064, "count": 1, "self": 0.15860043099974064 } } } } } } }