{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.787154495716095, "min": 0.787154495716095, "max": 2.8355491161346436, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7481.1162109375, "min": 7481.1162109375, "max": 28945.28515625, "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": 13.331162452697754, "min": 0.4243287146091461, "max": 13.331162452697754, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2599.57666015625, "min": 82.31977081298828, "max": 2717.002197265625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0714255362775065, "min": 0.06216203640158032, "max": 0.0743758514254153, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.285702145110026, "min": 0.25022462364565806, "max": 0.37187925712707653, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18007841490793464, "min": 0.1417073276186106, "max": 0.28154302600259873, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7203136596317385, "min": 0.5668293104744424, "max": 1.2936269690593083, "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.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.Environment.CumulativeReward.mean": { "value": 25.977272727272727, "min": 3.840909090909091, "max": 26.2, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1143.0, "min": 169.0, "max": 1441.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.977272727272727, "min": 3.840909090909091, "max": 26.2, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1143.0, "min": 169.0, "max": 1441.0, "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": "1785335008", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785335623" }, "total": 614.7955799869999, "count": 1, "self": 0.6449927310000021, "children": { "run_training.setup": { "total": 0.03493304500011618, "count": 1, "self": 0.03493304500011618 }, "TrainerController.start_learning": { "total": 614.1156542109998, "count": 1, "self": 0.6506506410307793, "children": { "TrainerController._reset_env": { "total": 3.840716272999998, "count": 1, "self": 3.840716272999998 }, "TrainerController.advance": { "total": 609.5518338539689, "count": 18192, "self": 0.669109886986007, "children": { "env_step": { "total": 444.49219213998435, "count": 18192, "self": 388.1800872030142, "children": { "SubprocessEnvManager._take_step": { "total": 55.921653030990456, "count": 18192, "self": 2.192245026986029, "children": { "TorchPolicy.evaluate": { "total": 53.729408004004426, "count": 18192, "self": 53.729408004004426 } } }, "workers": { "total": 0.3904519059797167, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 611.0133892449905, "count": 18192, "is_parallel": true, "self": 275.8129677919899, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056609780001508625, "count": 1, "is_parallel": true, "self": 0.004012354000678897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016486239994719654, "count": 10, "is_parallel": true, "self": 0.0016486239994719654 } } }, "UnityEnvironment.step": { "total": 0.04761697499998263, "count": 1, "is_parallel": true, "self": 0.0007784730003095319, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046850199987602537, "count": 1, "is_parallel": true, "self": 0.00046850199987602537 }, "communicator.exchange": { "total": 0.04412192899985712, "count": 1, "is_parallel": true, "self": 0.04412192899985712 }, "steps_from_proto": { "total": 0.002248070999939955, "count": 1, "is_parallel": true, "self": 0.0004669670004204818, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017811039995194733, "count": 10, "is_parallel": true, "self": 0.0017811039995194733 } } } } } } }, "UnityEnvironment.step": { "total": 335.2004214530007, "count": 18191, "is_parallel": true, "self": 15.836605384017048, "children": { "UnityEnvironment._generate_step_input": { "total": 8.20556153798293, "count": 18191, "is_parallel": true, "self": 8.20556153798293 }, "communicator.exchange": { "total": 258.81647728699136, "count": 18191, "is_parallel": true, "self": 258.81647728699136 }, "steps_from_proto": { "total": 52.341777244009336, "count": 18191, "is_parallel": true, "self": 9.528511355986893, "children": { "_process_rank_one_or_two_observation": { "total": 42.81326588802244, "count": 181910, "is_parallel": true, "self": 42.81326588802244 } } } } } } } } } } }, "trainer_advance": { "total": 164.39053182699854, "count": 18192, "self": 0.9197488659870032, "children": { "process_trajectory": { "total": 30.672055452011136, "count": 18192, "self": 30.26050710601112, "children": { "RLTrainer._checkpoint": { "total": 0.4115483460000178, "count": 4, "self": 0.4115483460000178 } } }, "_update_policy": { "total": 132.7987275090004, "count": 90, "self": 48.90366724001069, "children": { "TorchPPOOptimizer.update": { "total": 83.89506026898971, "count": 4587, "self": 83.89506026898971 } } } } } } }, "trainer_threads": { "total": 9.720001798996236e-07, "count": 1, "self": 9.720001798996236e-07 }, "TrainerController._save_models": { "total": 0.07245247099990593, "count": 1, "self": 0.0009503649998805486, "children": { "RLTrainer._checkpoint": { "total": 0.07150210600002538, "count": 1, "self": 0.07150210600002538 } } } } } } }