{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9209413528442383, "min": 0.9209413528442383, "max": 2.871856689453125, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8783.017578125, "min": 8783.017578125, "max": 29410.685546875, "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": 12.7389497756958, "min": 0.3018515408039093, "max": 12.7389497756958, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2484.09521484375, "min": 58.55919647216797, "max": 2585.9873046875, "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": 0.0706590094515716, "min": 0.05669400394186132, "max": 0.07430721730605572, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2826360378062864, "min": 0.22677601576744527, "max": 0.3715360865302786, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20916410506355995, "min": 0.10901821098135163, "max": 0.29167981621097117, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8366564202542398, "min": 0.4360728439254065, "max": 1.458399081054856, "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": 25.34090909090909, "min": 3.4545454545454546, "max": 25.34090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1115.0, "min": 152.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.34090909090909, "min": 3.4545454545454546, "max": 25.34090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1115.0, "min": 152.0, "max": 1381.0, "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": "1698259680", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698260145" }, "total": 464.8662463669999, "count": 1, "self": 0.4248770509998394, "children": { "run_training.setup": { "total": 0.07012622899992493, "count": 1, "self": 0.07012622899992493 }, "TrainerController.start_learning": { "total": 464.37124308700015, "count": 1, "self": 0.5568074330049058, "children": { "TrainerController._reset_env": { "total": 8.616215809999971, "count": 1, "self": 8.616215809999971 }, "TrainerController.advance": { "total": 455.11464672399507, "count": 18199, "self": 0.2635728959991184, "children": { "env_step": { "total": 454.85107382799595, "count": 18199, "self": 310.9022596389889, "children": { "SubprocessEnvManager._take_step": { "total": 143.6700327440044, "count": 18199, "self": 1.433619640005304, "children": { "TorchPolicy.evaluate": { "total": 142.2364131039991, "count": 18199, "self": 142.2364131039991 } } }, "workers": { "total": 0.27878144500266444, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 463.1922457739994, "count": 18199, "is_parallel": true, "self": 227.64895836300275, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00658376599994881, "count": 1, "is_parallel": true, "self": 0.004238191999888841, "children": { "_process_rank_one_or_two_observation": { "total": 0.002345574000059969, "count": 10, "is_parallel": true, "self": 0.002345574000059969 } } }, "UnityEnvironment.step": { "total": 0.04747549900002923, "count": 1, "is_parallel": true, "self": 0.0006043309999768098, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000329011000076207, "count": 1, "is_parallel": true, "self": 0.000329011000076207 }, "communicator.exchange": { "total": 0.044608176999986426, "count": 1, "is_parallel": true, "self": 0.044608176999986426 }, "steps_from_proto": { "total": 0.0019339799999897878, "count": 1, "is_parallel": true, "self": 0.0003785349997542653, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015554450002355225, "count": 10, "is_parallel": true, "self": 0.0015554450002355225 } } } } } } }, "UnityEnvironment.step": { "total": 235.54328741099664, "count": 18198, "is_parallel": true, "self": 10.481470879992457, "children": { "UnityEnvironment._generate_step_input": { "total": 5.277637738007229, "count": 18198, "is_parallel": true, "self": 5.277637738007229 }, "communicator.exchange": { "total": 186.65906805500106, "count": 18198, "is_parallel": true, "self": 186.65906805500106 }, "steps_from_proto": { "total": 33.1251107379959, "count": 18198, "is_parallel": true, "self": 6.1523711069964975, "children": { "_process_rank_one_or_two_observation": { "total": 26.9727396309994, "count": 181980, "is_parallel": true, "self": 26.9727396309994 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012975600020581624, "count": 1, "self": 0.00012975600020581624, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 451.3665335329466, "count": 478805, "is_parallel": true, "self": 10.086205641934612, "children": { "process_trajectory": { "total": 255.24426894801184, "count": 478805, "is_parallel": true, "self": 254.73951158601164, "children": { "RLTrainer._checkpoint": { "total": 0.5047573620001913, "count": 4, "is_parallel": true, "self": 0.5047573620001913 } } }, "_update_policy": { "total": 186.03605894300017, "count": 90, "is_parallel": true, "self": 56.227901738001606, "children": { "TorchPPOOptimizer.update": { "total": 129.80815720499857, "count": 4587, "is_parallel": true, "self": 129.80815720499857 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0834433640000043, "count": 1, "self": 0.0008558209999591782, "children": { "RLTrainer._checkpoint": { "total": 0.08258754300004512, "count": 1, "self": 0.08258754300004512 } } } } } } }