{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0229042768478394, "min": 1.0229042768478394, "max": 2.8707146644592285, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9811.6982421875, "min": 9811.6982421875, "max": 29398.98828125, "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": 12.706707954406738, "min": 0.37706705927848816, "max": 12.711974143981934, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2477.80810546875, "min": 73.15100860595703, "max": 2593.24267578125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0673919844979822, "min": 0.06518774090378143, "max": 0.0734625206911433, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2695679379919288, "min": 0.26075096361512573, "max": 0.35868245851227526, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1993488193142648, "min": 0.11312252113152771, "max": 0.2934625228392143, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7973952772570592, "min": 0.45249008452611084, "max": 1.4007167287316977, "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": 25.113636363636363, "min": 3.0681818181818183, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 135.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 3.0681818181818183, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 135.0, "max": 1378.0, "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": "1691320932", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1691321468" }, "total": 536.581390691, "count": 1, "self": 0.7915966649998154, "children": { "run_training.setup": { "total": 0.04578102300001774, "count": 1, "self": 0.04578102300001774 }, "TrainerController.start_learning": { "total": 535.7440130030002, "count": 1, "self": 0.7227172780185356, "children": { "TrainerController._reset_env": { "total": 6.626982606999945, "count": 1, "self": 6.626982606999945 }, "TrainerController.advance": { "total": 528.1390055249819, "count": 18219, "self": 0.3484290750106993, "children": { "env_step": { "total": 527.7905764499712, "count": 18219, "self": 386.5593055139623, "children": { "SubprocessEnvManager._take_step": { "total": 140.87713453198876, "count": 18219, "self": 2.126474087964425, "children": { "TorchPolicy.evaluate": { "total": 138.75066044402433, "count": 18219, "self": 138.75066044402433 } } }, "workers": { "total": 0.35413640402020974, "count": 18219, "self": 0.0, "children": { "worker_root": { "total": 533.774166872992, "count": 18219, "is_parallel": true, "self": 247.13209582799868, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005639757999915673, "count": 1, "is_parallel": true, "self": 0.004052485999864075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015872720000515983, "count": 10, "is_parallel": true, "self": 0.0015872720000515983 } } }, "UnityEnvironment.step": { "total": 0.055288012999881175, "count": 1, "is_parallel": true, "self": 0.000544753999747627, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041435499997533043, "count": 1, "is_parallel": true, "self": 0.00041435499997533043 }, "communicator.exchange": { "total": 0.05192156100019929, "count": 1, "is_parallel": true, "self": 0.05192156100019929 }, "steps_from_proto": { "total": 0.002407342999958928, "count": 1, "is_parallel": true, "self": 0.0004158599999755097, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019914829999834183, "count": 10, "is_parallel": true, "self": 0.0019914829999834183 } } } } } } }, "UnityEnvironment.step": { "total": 286.6420710449934, "count": 18218, "is_parallel": true, "self": 11.997053849995382, "children": { "UnityEnvironment._generate_step_input": { "total": 6.040061294011593, "count": 18218, "is_parallel": true, "self": 6.040061294011593 }, "communicator.exchange": { "total": 226.79045829300867, "count": 18218, "is_parallel": true, "self": 226.79045829300867 }, "steps_from_proto": { "total": 41.81449760797773, "count": 18218, "is_parallel": true, "self": 7.947338302911476, "children": { "_process_rank_one_or_two_observation": { "total": 33.86715930506625, "count": 182180, "is_parallel": true, "self": 33.86715930506625 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019443399992269406, "count": 1, "self": 0.00019443399992269406, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 523.9024801668854, "count": 494216, "is_parallel": true, "self": 11.741714307981738, "children": { "process_trajectory": { "total": 291.62790602490145, "count": 494216, "is_parallel": true, "self": 290.18433492390113, "children": { "RLTrainer._checkpoint": { "total": 1.443571101000316, "count": 4, "is_parallel": true, "self": 1.443571101000316 } } }, "_update_policy": { "total": 220.53285983400224, "count": 90, "is_parallel": true, "self": 84.08470099100941, "children": { "TorchPPOOptimizer.update": { "total": 136.44815884299283, "count": 4587, "is_parallel": true, "self": 136.44815884299283 } } } } } } } } }, "TrainerController._save_models": { "total": 0.25511315899984766, "count": 1, "self": 0.0012444789997516637, "children": { "RLTrainer._checkpoint": { "total": 0.253868680000096, "count": 1, "self": 0.253868680000096 } } } } } } }