{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9460627436637878, "min": 0.940580427646637, "max": 2.8725709915161133, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9074.6337890625, "min": 9074.6337890625, "max": 29481.197265625, "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": 12.76462459564209, "min": 0.25665125250816345, "max": 12.76462459564209, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2489.101806640625, "min": 49.790340423583984, "max": 2573.892578125, "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": 0.06578439509258696, "min": 0.06403154974139076, "max": 0.07485416185626688, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26313758037034785, "min": 0.25612619896556305, "max": 0.3742708092813344, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20846296803039663, "min": 0.1048034507137559, "max": 0.30363876759713776, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8338518721215865, "min": 0.4192138028550236, "max": 1.3159625121191436, "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": 24.772727272727273, "min": 2.8636363636363638, "max": 25.21818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1090.0, "min": 126.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.772727272727273, "min": 2.8636363636363638, "max": 25.21818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1090.0, "min": 126.0, "max": 1387.0, "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": "1699605787", "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=SnowballTarget --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": "1699606356" }, "total": 569.38917941, "count": 1, "self": 1.1008083499999657, "children": { "run_training.setup": { "total": 0.06765632599999094, "count": 1, "self": 0.06765632599999094 }, "TrainerController.start_learning": { "total": 568.220714734, "count": 1, "self": 0.8125421229949552, "children": { "TrainerController._reset_env": { "total": 1.576408114000003, "count": 1, "self": 1.576408114000003 }, "TrainerController.advance": { "total": 565.682247251005, "count": 18209, "self": 0.4177191500060644, "children": { "env_step": { "total": 565.264528100999, "count": 18209, "self": 445.18252847199994, "children": { "SubprocessEnvManager._take_step": { "total": 119.69344898799358, "count": 18209, "self": 2.3013642759945867, "children": { "TorchPolicy.evaluate": { "total": 117.39208471199899, "count": 18209, "self": 117.39208471199899 } } }, "workers": { "total": 0.3885506410054518, "count": 18209, "self": 0.0, "children": { "worker_root": { "total": 566.1762033770098, "count": 18209, "is_parallel": true, "self": 255.3529255040046, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.01059595200001695, "count": 1, "is_parallel": true, "self": 0.009038989000032416, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015569629999845347, "count": 10, "is_parallel": true, "self": 0.0015569629999845347 } } }, "UnityEnvironment.step": { "total": 0.06470314800000665, "count": 1, "is_parallel": true, "self": 0.0007529479999845989, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045687100001146064, "count": 1, "is_parallel": true, "self": 0.00045687100001146064 }, "communicator.exchange": { "total": 0.061140999000002694, "count": 1, "is_parallel": true, "self": 0.061140999000002694 }, "steps_from_proto": { "total": 0.002352330000007896, "count": 1, "is_parallel": true, "self": 0.00048416000001338944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018681699999945067, "count": 10, "is_parallel": true, "self": 0.0018681699999945067 } } } } } } }, "UnityEnvironment.step": { "total": 310.82327787300517, "count": 18208, "is_parallel": true, "self": 14.35673391301259, "children": { "UnityEnvironment._generate_step_input": { "total": 7.528467093001666, "count": 18208, "is_parallel": true, "self": 7.528467093001666 }, "communicator.exchange": { "total": 244.6646523389985, "count": 18208, "is_parallel": true, "self": 244.6646523389985 }, "steps_from_proto": { "total": 44.273424527992404, "count": 18208, "is_parallel": true, "self": 8.763873791960748, "children": { "_process_rank_one_or_two_observation": { "total": 35.509550736031656, "count": 182080, "is_parallel": true, "self": 35.509550736031656 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019202900000436784, "count": 1, "self": 0.00019202900000436784, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 560.2413061609778, "count": 597128, "is_parallel": true, "self": 14.083634612993137, "children": { "process_trajectory": { "total": 311.0623427889848, "count": 597128, "is_parallel": true, "self": 309.4798622849848, "children": { "RLTrainer._checkpoint": { "total": 1.5824805039999887, "count": 4, "is_parallel": true, "self": 1.5824805039999887 } } }, "_update_policy": { "total": 235.09532875899993, "count": 90, "is_parallel": true, "self": 70.57550424099693, "children": { "TorchPPOOptimizer.update": { "total": 164.519824518003, "count": 4587, "is_parallel": true, "self": 164.519824518003 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14932521699995505, "count": 1, "self": 0.0022278899999719215, "children": { "RLTrainer._checkpoint": { "total": 0.14709732699998312, "count": 1, "self": 0.14709732699998312 } } } } } } }