{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9393413066864014, "min": 0.9393413066864014, "max": 2.8642983436584473, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9030.8271484375, "min": 9030.8271484375, "max": 29364.787109375, "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": 12.620147705078125, "min": 0.3448663353919983, "max": 12.620147705078125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2460.9287109375, "min": 66.90406799316406, "max": 2543.75146484375, "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": 0.07102454725057161, "min": 0.06125755637938923, "max": 0.07741545979542266, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28409818900228645, "min": 0.24695958728604156, "max": 0.3870772989771133, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1880379229710967, "min": 0.11958992370180603, "max": 0.27823135794377796, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7521516918843868, "min": 0.4783596948072241, "max": 1.3911567897188897, "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": 24.522727272727273, "min": 3.409090909090909, "max": 25.254545454545454, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1079.0, "min": 150.0, "max": 1389.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.522727272727273, "min": 3.409090909090909, "max": 25.254545454545454, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1079.0, "min": 150.0, "max": 1389.0, "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": "1679687960", "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": "1679688419" }, "total": 458.835747158, "count": 1, "self": 0.7391259949999949, "children": { "run_training.setup": { "total": 0.11227528300003087, "count": 1, "self": 0.11227528300003087 }, "TrainerController.start_learning": { "total": 457.98434588, "count": 1, "self": 0.5180594200041355, "children": { "TrainerController._reset_env": { "total": 9.109462468000004, "count": 1, "self": 9.109462468000004 }, "TrainerController.advance": { "total": 448.14824400399584, "count": 18223, "self": 0.26779560298621163, "children": { "env_step": { "total": 447.88044840100963, "count": 18223, "self": 324.6184028170193, "children": { "SubprocessEnvManager._take_step": { "total": 122.99771835299964, "count": 18223, "self": 2.0248411120026617, "children": { "TorchPolicy.evaluate": { "total": 120.97287724099698, "count": 18223, "self": 120.97287724099698 } } }, "workers": { "total": 0.2643272309907161, "count": 18223, "self": 0.0, "children": { "worker_root": { "total": 456.5242124210034, "count": 18223, "is_parallel": true, "self": 218.79444262801684, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006748926999989635, "count": 1, "is_parallel": true, "self": 0.0050653539998961605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016835730000934745, "count": 10, "is_parallel": true, "self": 0.0016835730000934745 } } }, "UnityEnvironment.step": { "total": 0.08663796900003717, "count": 1, "is_parallel": true, "self": 0.0006069909999837364, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040661799999952564, "count": 1, "is_parallel": true, "self": 0.00040661799999952564 }, "communicator.exchange": { "total": 0.08313272500004132, "count": 1, "is_parallel": true, "self": 0.08313272500004132 }, "steps_from_proto": { "total": 0.002491635000012593, "count": 1, "is_parallel": true, "self": 0.0010524199998940276, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014392150001185655, "count": 10, "is_parallel": true, "self": 0.0014392150001185655 } } } } } } }, "UnityEnvironment.step": { "total": 237.7297697929866, "count": 18222, "is_parallel": true, "self": 9.522866171985186, "children": { "UnityEnvironment._generate_step_input": { "total": 5.1186592810069556, "count": 18222, "is_parallel": true, "self": 5.1186592810069556 }, "communicator.exchange": { "total": 192.48441908400235, "count": 18222, "is_parallel": true, "self": 192.48441908400235 }, "steps_from_proto": { "total": 30.603825255992092, "count": 18222, "is_parallel": true, "self": 5.935672744982469, "children": { "_process_rank_one_or_two_observation": { "total": 24.668152511009623, "count": 182220, "is_parallel": true, "self": 24.668152511009623 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011418199994750466, "count": 1, "self": 0.00011418199994750466, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 444.88723996001136, "count": 387648, "is_parallel": true, "self": 9.59442458499683, "children": { "process_trajectory": { "total": 246.59494916801395, "count": 387648, "is_parallel": true, "self": 245.11202591601398, "children": { "RLTrainer._checkpoint": { "total": 1.4829232519999778, "count": 4, "is_parallel": true, "self": 1.4829232519999778 } } }, "_update_policy": { "total": 188.69786620700057, "count": 90, "is_parallel": true, "self": 70.03810177700984, "children": { "TorchPPOOptimizer.update": { "total": 118.65976442999073, "count": 4587, "is_parallel": true, "self": 118.65976442999073 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20846580600004927, "count": 1, "self": 0.0011668440000676128, "children": { "RLTrainer._checkpoint": { "total": 0.20729896199998166, "count": 1, "self": 0.20729896199998166 } } } } } } }