{ "name": "root", "gauges": { "PushBlock.Policy.Entropy.mean": { "value": 0.2016972005367279, "min": 0.18549907207489014, "max": 1.8744633197784424, "count": 50 }, "PushBlock.Policy.Entropy.sum": { "value": 12082.46875, "min": 11112.13671875, "max": 113727.4375, "count": 50 }, "PushBlock.Step.mean": { "value": 2999995.0, "min": 59981.0, "max": 2999995.0, "count": 50 }, "PushBlock.Step.sum": { "value": 2999995.0, "min": 59981.0, "max": 2999995.0, "count": 50 }, "PushBlock.Policy.ExtrinsicValueEstimate.mean": { "value": 4.532731533050537, "min": 0.06312137842178345, "max": 4.55885124206543, "count": 50 }, "PushBlock.Policy.ExtrinsicValueEstimate.sum": { "value": 15116.66015625, "min": 60.53340148925781, "max": 15470.3671875, "count": 50 }, "PushBlock.Losses.PolicyLoss.mean": { "value": 0.06696407760636634, "min": 0.06569872397478488, "max": 0.07140306353799185, "count": 50 }, "PushBlock.Losses.PolicyLoss.sum": { "value": 1.941958250584624, "min": 1.4558263342006108, "max": 2.0864144192310055, "count": 50 }, "PushBlock.Losses.ValueLoss.mean": { "value": 0.06186323563217709, "min": 0.03626665951959768, "max": 0.3553684272410749, "count": 50 }, "PushBlock.Losses.ValueLoss.sum": { "value": 1.7940338333331356, "min": 1.0517331260683327, "max": 10.305684389991173, "count": 50 }, "PushBlock.Policy.LearningRate.mean": { "value": 3.087381729526438e-06, "min": 3.087381729526438e-06, "max": 0.0002966075106546396, "count": 50 }, "PushBlock.Policy.LearningRate.sum": { "value": 8.95340701562667e-05, "min": 8.95340701562667e-05, "max": 0.0084374907875031, "count": 50 }, "PushBlock.Policy.Epsilon.mean": { "value": 0.10102909425287358, "min": 0.10102909425287358, "max": 0.19886916984126987, "count": 50 }, "PushBlock.Policy.Epsilon.sum": { "value": 2.929843733333334, "min": 2.929843733333334, "max": 5.7124969, "count": 50 }, "PushBlock.Policy.Beta.mean": { "value": 0.00011280651586206898, "min": 0.00011280651586206898, "max": 0.009887030067142857, "count": 50 }, "PushBlock.Policy.Beta.sum": { "value": 0.0032713889600000006, "min": 0.0032713889600000006, "max": 0.28125844031, "count": 50 }, "PushBlock.Environment.EpisodeLength.mean": { "value": 17.034724337496193, "min": 16.847930413917215, "max": 804.1730769230769, "count": 50 }, "PushBlock.Environment.EpisodeLength.sum": { "value": 55925.0, "min": 41817.0, "max": 74923.0, "count": 50 }, "PushBlock.Environment.CumulativeReward.mean": { "value": 4.9793144792735795, "min": 1.1180461471757064, "max": 4.980931816069633, "count": 50 }, "PushBlock.Environment.CumulativeReward.sum": { "value": 16352.068749934435, "min": 58.13839965313673, "max": 16760.835561074317, "count": 50 }, "PushBlock.Policy.ExtrinsicReward.mean": { "value": 4.9793144792735795, "min": 1.1180461471757064, "max": 4.980931816069633, "count": 50 }, "PushBlock.Policy.ExtrinsicReward.sum": { "value": 16352.068749934435, "min": 58.13839965313673, "max": 16760.835561074317, "count": 50 }, "PushBlock.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "PushBlock.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1661438077", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PushBlock.yaml --env=./trained-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1661441051" }, "total": 2974.1935982289997, "count": 1, "self": 0.2708926149994113, "children": { "run_training.setup": { "total": 0.03884206900011122, "count": 1, "self": 0.03884206900011122 }, "TrainerController.start_learning": { "total": 2973.883863545, "count": 1, "self": 4.222226816023522, "children": { "TrainerController._reset_env": { "total": 5.337355265000042, "count": 1, "self": 5.337355265000042 }, "TrainerController.advance": { "total": 2964.264817552976, "count": 183916, "self": 4.029414248805097, "children": { "env_step": { "total": 1667.2106005960522, "count": 183916, "self": 1517.0580446200443, "children": { "SubprocessEnvManager._take_step": { "total": 148.06953378606113, "count": 183916, "self": 8.418083007220957, "children": { "TorchPolicy.evaluate": { "total": 139.65145077884017, "count": 93759, "self": 46.02098987685531, "children": { "TorchPolicy.sample_actions": { "total": 93.63046090198486, "count": 93759, "self": 93.63046090198486 } } } } }, "workers": { "total": 2.0830221899468597, "count": 183916, "self": 0.0, "children": { "worker_root": { "total": 2967.5151370739154, "count": 183916, "is_parallel": true, "self": 1695.8266128530695, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059622110002237605, "count": 1, "is_parallel": true, "self": 0.004477401999793074, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014848090004306869, "count": 4, "is_parallel": true, "self": 0.0014848090004306869 } } }, "UnityEnvironment.step": { "total": 0.026541934999841033, "count": 1, "is_parallel": true, "self": 0.0005433209998955135, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043376699977670796, "count": 1, "is_parallel": true, "self": 0.00043376699977670796 }, "communicator.exchange": { "total": 0.02414151299990408, "count": 1, "is_parallel": true, "self": 0.02414151299990408 }, "steps_from_proto": { "total": 0.001423334000264731, "count": 1, "is_parallel": true, "self": 0.00033219399983863696, "children": { "_process_rank_one_or_two_observation": { "total": 0.001091140000426094, "count": 4, "is_parallel": true, "self": 0.001091140000426094 } } } } } } }, "UnityEnvironment.step": { "total": 1271.688524220846, "count": 183915, "is_parallel": true, "self": 47.46229449071143, "children": { "UnityEnvironment._generate_step_input": { "total": 35.0671926720247, "count": 183915, "is_parallel": true, "self": 35.0671926720247 }, "communicator.exchange": { "total": 1044.1114959289575, "count": 183915, "is_parallel": true, "self": 1044.1114959289575 }, "steps_from_proto": { "total": 145.04754112915225, "count": 183915, "is_parallel": true, "self": 35.15162142514737, "children": { "_process_rank_one_or_two_observation": { "total": 109.89591970400488, "count": 735660, "is_parallel": true, "self": 109.89591970400488 } } } } } } } } } } }, "trainer_advance": { "total": 1293.0248027081188, "count": 183916, "self": 6.962872703143603, "children": { "process_trajectory": { "total": 437.8201000129616, "count": 183916, "self": 437.4436326859609, "children": { "RLTrainer._checkpoint": { "total": 0.3764673270006824, "count": 6, "self": 0.3764673270006824 } } }, "_update_policy": { "total": 848.2418299920137, "count": 1443, "self": 461.6994568790328, "children": { "TorchPPOOptimizer.update": { "total": 386.54237311298084, "count": 69624, "self": 386.54237311298084 } } } } } } }, "trainer_threads": { "total": 1.1199999789823778e-06, "count": 1, "self": 1.1199999789823778e-06 }, "TrainerController._save_models": { "total": 0.05946279100044194, "count": 1, "self": 0.0007346769998548552, "children": { "RLTrainer._checkpoint": { "total": 0.058728114000587084, "count": 1, "self": 0.058728114000587084 } } } } } } }