{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9088402986526489, "min": 0.8937181830406189, "max": 2.8631064891815186, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8697.6015625, "min": 8697.6015625, "max": 29352.568359375, "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": 12.608723640441895, "min": 0.3360554277896881, "max": 12.608723640441895, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2458.701171875, "min": 65.19475555419922, "max": 2561.248291015625, "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.Losses.PolicyLoss.mean": { "value": 0.06621884418763882, "min": 0.06125280892009708, "max": 0.07350009413829528, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2648753767505553, "min": 0.24501123568038832, "max": 0.3594707475196771, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20160755011088707, "min": 0.11717101496269963, "max": 0.282286379793111, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8064302004435483, "min": 0.46868405985079853, "max": 1.411431898965555, "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.CumulativeReward.mean": { "value": 24.727272727272727, "min": 3.5681818181818183, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1088.0, "min": 157.0, "max": 1350.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.727272727272727, "min": 3.5681818181818183, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1088.0, "min": 157.0, "max": 1350.0, "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": "1681615509", "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": "1681615951" }, "total": 441.86717224899996, "count": 1, "self": 0.43254473599995436, "children": { "run_training.setup": { "total": 0.10945605400002023, "count": 1, "self": 0.10945605400002023 }, "TrainerController.start_learning": { "total": 441.325171459, "count": 1, "self": 0.5085324299966487, "children": { "TrainerController._reset_env": { "total": 4.780267001000027, "count": 1, "self": 4.780267001000027 }, "TrainerController.advance": { "total": 435.9064910870034, "count": 18204, "self": 0.2652669590114556, "children": { "env_step": { "total": 435.64122412799196, "count": 18204, "self": 316.8180979659882, "children": { "SubprocessEnvManager._take_step": { "total": 118.57208602600628, "count": 18204, "self": 1.6216455450057197, "children": { "TorchPolicy.evaluate": { "total": 116.95044048100056, "count": 18204, "self": 116.95044048100056 } } }, "workers": { "total": 0.25104013599747077, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 439.94143115699694, "count": 18204, "is_parallel": true, "self": 207.81405587699845, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0048652869999727955, "count": 1, "is_parallel": true, "self": 0.0034378529999230523, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014274340000497432, "count": 10, "is_parallel": true, "self": 0.0014274340000497432 } } }, "UnityEnvironment.step": { "total": 0.045632305999959044, "count": 1, "is_parallel": true, "self": 0.0007123839999394477, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004067130000180441, "count": 1, "is_parallel": true, "self": 0.0004067130000180441 }, "communicator.exchange": { "total": 0.04229213200000004, "count": 1, "is_parallel": true, "self": 0.04229213200000004 }, "steps_from_proto": { "total": 0.0022210770000015145, "count": 1, "is_parallel": true, "self": 0.00038941500002920293, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018316619999723116, "count": 10, "is_parallel": true, "self": 0.0018316619999723116 } } } } } } }, "UnityEnvironment.step": { "total": 232.1273752799985, "count": 18203, "is_parallel": true, "self": 9.581233993000183, "children": { "UnityEnvironment._generate_step_input": { "total": 5.135674592994576, "count": 18203, "is_parallel": true, "self": 5.135674592994576 }, "communicator.exchange": { "total": 187.1950557349951, "count": 18203, "is_parallel": true, "self": 187.1950557349951 }, "steps_from_proto": { "total": 30.215410959008636, "count": 18203, "is_parallel": true, "self": 5.829925834019491, "children": { "_process_rank_one_or_two_observation": { "total": 24.385485124989145, "count": 182030, "is_parallel": true, "self": 24.385485124989145 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001264689999516122, "count": 1, "self": 0.0001264689999516122, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 432.70129195495826, "count": 387925, "is_parallel": true, "self": 9.599453255965557, "children": { "process_trajectory": { "total": 238.05409949699316, "count": 387925, "is_parallel": true, "self": 237.31154557999326, "children": { "RLTrainer._checkpoint": { "total": 0.7425539169998956, "count": 4, "is_parallel": true, "self": 0.7425539169998956 } } }, "_update_policy": { "total": 185.04773920199955, "count": 90, "is_parallel": true, "self": 68.56556495600375, "children": { "TorchPPOOptimizer.update": { "total": 116.4821742459958, "count": 4587, "is_parallel": true, "self": 116.4821742459958 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12975447199994505, "count": 1, "self": 0.0008996779999961291, "children": { "RLTrainer._checkpoint": { "total": 0.12885479399994892, "count": 1, "self": 0.12885479399994892 } } } } } } }