{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7914053201675415, "min": 0.7395239472389221, "max": 1.0724937915802002, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8061.2548828125, "min": 7238.7158203125, "max": 10983.4091796875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 399968.0, "min": 209936.0, "max": 399968.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 399968.0, "min": 209936.0, "max": 399968.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.424694061279297, "min": 12.863568305969238, "max": 13.596199989318848, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2617.8154296875, "min": 2469.80517578125, "max": 2767.04541015625, "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": 0.06790241125261175, "min": 0.06417496013826024, "max": 0.07435267957253197, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.271609645010447, "min": 0.25669984055304096, "max": 0.37176339786265983, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19967366433611103, "min": 0.16358210274255744, "max": 0.2097026512611146, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7986946573444441, "min": 0.6543284109702298, "max": 1.048513256305573, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.957098681000002e-06, "min": 3.957098681000002e-06, "max": 0.000145857051381, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.582839472400001e-05, "min": 1.582839472400001e-05, "max": 0.00069216026928, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101319, "min": 0.101319, "max": 0.14861900000000003, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.405276, "min": 0.405276, "max": 0.73072, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.581810000000006e-05, "min": 7.581810000000006e-05, "max": 0.0024360881000000003, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00030327240000000024, "min": 0.00030327240000000024, "max": 0.011562928000000002, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.136363636363637, "min": 25.40909090909091, "max": 26.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1150.0, "min": 1118.0, "max": 1465.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.136363636363637, "min": 25.40909090909091, "max": 26.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1150.0, "min": 1118.0, "max": 1465.0, "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": "1679878874", "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 --resume", "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": "1679879452" }, "total": 578.5950579900002, "count": 1, "self": 0.7875139050004236, "children": { "run_training.setup": { "total": 0.12787517399988246, "count": 1, "self": 0.12787517399988246 }, "TrainerController.start_learning": { "total": 577.6796689109999, "count": 1, "self": 0.8763217719767908, "children": { "TrainerController._reset_env": { "total": 3.541371915999889, "count": 1, "self": 3.541371915999889 }, "TrainerController.advance": { "total": 573.0206384500232, "count": 18217, "self": 0.4247037960265061, "children": { "env_step": { "total": 572.5959346539967, "count": 18217, "self": 461.32161100900294, "children": { "SubprocessEnvManager._take_step": { "total": 110.86947813401434, "count": 18217, "self": 2.5469452100292074, "children": { "TorchPolicy.evaluate": { "total": 108.32253292398514, "count": 18217, "self": 108.32253292398514 } } }, "workers": { "total": 0.4048455109793849, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 575.5761968960053, "count": 18217, "is_parallel": true, "self": 254.10359240097273, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002231082999969658, "count": 1, "is_parallel": true, "self": 0.0006481899997652363, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015828930002044217, "count": 10, "is_parallel": true, "self": 0.0015828930002044217 } } }, "UnityEnvironment.step": { "total": 0.050761229000045205, "count": 1, "is_parallel": true, "self": 0.0006805990001339524, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003413889999137609, "count": 1, "is_parallel": true, "self": 0.0003413889999137609 }, "communicator.exchange": { "total": 0.04752009300000282, "count": 1, "is_parallel": true, "self": 0.04752009300000282 }, "steps_from_proto": { "total": 0.002219147999994675, "count": 1, "is_parallel": true, "self": 0.0004505099996094941, "children": { "_process_rank_one_or_two_observation": { "total": 0.001768638000385181, "count": 10, "is_parallel": true, "self": 0.001768638000385181 } } } } } } }, "UnityEnvironment.step": { "total": 321.47260449503256, "count": 18216, "is_parallel": true, "self": 12.923220877001768, "children": { "UnityEnvironment._generate_step_input": { "total": 6.977096945038056, "count": 18216, "is_parallel": true, "self": 6.977096945038056 }, "communicator.exchange": { "total": 259.1599640960078, "count": 18216, "is_parallel": true, "self": 259.1599640960078 }, "steps_from_proto": { "total": 42.412322576984934, "count": 18216, "is_parallel": true, "self": 8.915250689944742, "children": { "_process_rank_one_or_two_observation": { "total": 33.49707188704019, "count": 182160, "is_parallel": true, "self": 33.49707188704019 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00034158600010414375, "count": 1, "self": 0.00034158600010414375, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 567.4594976457272, "count": 645045, "is_parallel": true, "self": 15.776210985784019, "children": { "process_trajectory": { "total": 305.99285114094437, "count": 645045, "is_parallel": true, "self": 304.0477899739442, "children": { "RLTrainer._checkpoint": { "total": 1.9450611670001763, "count": 4, "is_parallel": true, "self": 1.9450611670001763 } } }, "_update_policy": { "total": 245.6904355189988, "count": 90, "is_parallel": true, "self": 83.20750559399994, "children": { "TorchPPOOptimizer.update": { "total": 162.48292992499887, "count": 4587, "is_parallel": true, "self": 162.48292992499887 } } } } } } } } }, "TrainerController._save_models": { "total": 0.24099518699995315, "count": 1, "self": 0.0031808020003154525, "children": { "RLTrainer._checkpoint": { "total": 0.2378143849996377, "count": 1, "self": 0.2378143849996377 } } } } } } }