{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.2187771797180176, "min": 2.2187771797180176, "max": 2.872894525527954, "count": 7 }, "SnowballTarget.Policy.Entropy.sum": { "value": 22551.650390625, "min": 21930.828125, "max": 29484.515625, "count": 7 }, "SnowballTarget.Step.mean": { "value": 69992.0, "min": 9952.0, "max": 69992.0, "count": 7 }, "SnowballTarget.Step.sum": { "value": 69992.0, "min": 9952.0, "max": 69992.0, "count": 7 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 6.13842248916626, "min": 0.26918789744377136, "max": 6.13842248916626, "count": 7 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1196.992431640625, "min": 52.22245407104492, "max": 1196.992431640625, "count": 7 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 7 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 7 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0701628010642975, "min": 0.06406399848478317, "max": 0.07446456672623754, "count": 7 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28065120425719, "min": 0.2748059428143225, "max": 0.3723228336311877, "count": 7 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2767121357952847, "min": 0.10886514971977759, "max": 0.2868332563662061, "count": 7 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1068485431811388, "min": 0.43546059887911037, "max": 1.4341662818310306, "count": 7 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.2234378302857144e-05, "min": 2.2234378302857144e-05, "max": 0.00027680572201714283, "count": 7 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.893751321142857e-05, "min": 8.893751321142857e-05, "max": 0.001171885823657143, "count": 7 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10741142857142857, "min": 0.10741142857142857, "max": 0.19226857142857146, "count": 7 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4296457142857143, "min": 0.4296457142857143, "max": 0.8906285714285715, "count": 7 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0003798302857142858, "min": 0.0003798302857142858, "max": 0.004614201714285715, "count": 7 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0015193211428571431, "min": 0.0015193211428571431, "max": 0.019542365714285716, "count": 7 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 13.590909090909092, "min": 3.1363636363636362, "max": 13.590909090909092, "count": 7 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 598.0, "min": 138.0, "max": 740.0, "count": 7 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 13.590909090909092, "min": 3.1363636363636362, "max": 13.590909090909092, "count": 7 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 598.0, "min": 138.0, "max": 740.0, "count": 7 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719577142", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719577357" }, "total": 214.82278890799995, "count": 1, "self": 0.5976530020000155, "children": { "run_training.setup": { "total": 0.07652054900000849, "count": 1, "self": 0.07652054900000849 }, "TrainerController.start_learning": { "total": 214.14861535699993, "count": 1, "self": 0.3109908199988354, "children": { "TrainerController._reset_env": { "total": 3.3431707660000143, "count": 1, "self": 3.3431707660000143 }, "TrainerController.advance": { "total": 210.3870712280011, "count": 6403, "self": 0.15261164499935376, "children": { "env_step": { "total": 210.23445958300175, "count": 6403, "self": 161.4544984080074, "children": { "SubprocessEnvManager._take_step": { "total": 48.63277073899724, "count": 6403, "self": 0.8322956949996865, "children": { "TorchPolicy.evaluate": { "total": 47.80047504399755, "count": 6403, "self": 47.80047504399755 } } }, "workers": { "total": 0.14719043599711767, "count": 6403, "self": 0.0, "children": { "worker_root": { "total": 213.38263813600128, "count": 6403, "is_parallel": true, "self": 101.13606765800154, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009108892000028845, "count": 1, "is_parallel": true, "self": 0.007234721000031641, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018741709999972045, "count": 10, "is_parallel": true, "self": 0.0018741709999972045 } } }, "UnityEnvironment.step": { "total": 0.04323963699999922, "count": 1, "is_parallel": true, "self": 0.0008785629999579214, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043697400002429276, "count": 1, "is_parallel": true, "self": 0.00043697400002429276 }, "communicator.exchange": { "total": 0.039464795000014874, "count": 1, "is_parallel": true, "self": 0.039464795000014874 }, "steps_from_proto": { "total": 0.002459305000002132, "count": 1, "is_parallel": true, "self": 0.00046361000016759135, "children": { "_process_rank_one_or_two_observation": { "total": 0.001995694999834541, "count": 10, "is_parallel": true, "self": 0.001995694999834541 } } } } } } }, "UnityEnvironment.step": { "total": 112.24657047799974, "count": 6402, "is_parallel": true, "self": 5.290003811993017, "children": { "UnityEnvironment._generate_step_input": { "total": 2.709391321005228, "count": 6402, "is_parallel": true, "self": 2.709391321005228 }, "communicator.exchange": { "total": 88.34580896899996, "count": 6402, "is_parallel": true, "self": 88.34580896899996 }, "steps_from_proto": { "total": 15.901366376001533, "count": 6402, "is_parallel": true, "self": 3.1515482819906993, "children": { "_process_rank_one_or_two_observation": { "total": 12.749818094010834, "count": 64020, "is_parallel": true, "self": 12.749818094010834 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004331659999934345, "count": 1, "self": 0.0004331659999934345, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 207.9744821659766, "count": 280968, "is_parallel": true, "self": 6.3370124219535455, "children": { "process_trajectory": { "total": 112.97168614102321, "count": 280968, "is_parallel": true, "self": 110.84632215702317, "children": { "RLTrainer._checkpoint": { "total": 2.125363984000046, "count": 7, "is_parallel": true, "self": 2.125363984000046 } } }, "_update_policy": { "total": 88.66578360299985, "count": 31, "is_parallel": true, "self": 26.34424042499893, "children": { "TorchPPOOptimizer.update": { "total": 62.32154317800092, "count": 1578, "is_parallel": true, "self": 62.32154317800092 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10694937699997809, "count": 1, "self": 0.0018888829999923473, "children": { "RLTrainer._checkpoint": { "total": 0.10506049399998574, "count": 1, "self": 0.10506049399998574 } } } } } } }