{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5254992246627808, "min": 0.5015815496444702, "max": 0.7530991435050964, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5040.58837890625, "min": 4894.92529296875, "max": 7669.703125, "count": 30 }, "SnowballTarget.Step.mean": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.367341041564941, "min": 12.085987091064453, "max": 13.57891845703125, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2726.9375, "min": 2320.509521484375, "max": 2764.7763671875, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07120463558519488, "min": 0.058896382402499683, "max": 0.07685730606210521, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3560231779259744, "min": 0.23558552960999873, "max": 0.3651217979717972, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18280066923767913, "min": 0.15904425190506027, "max": 0.20083134256157223, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9140033461883956, "min": 0.6361770076202411, "max": 0.9642324411109382, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.1056989647999945e-06, "min": 3.1056989647999945e-06, "max": 0.00017668564110480002, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5528494823999972e-05, "min": 1.5528494823999972e-05, "max": 0.000853728215424, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10103520000000002, "min": 0.10103520000000002, "max": 0.15889520000000001, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5051760000000001, "min": 0.4120608, "max": 0.7845760000000002, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.165647999999992e-05, "min": 6.165647999999992e-05, "max": 0.002948870480000001, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003082823999999996, "min": 0.0003082823999999996, "max": 0.0142503424, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.254545454545454, "min": 24.15909090909091, "max": 26.70909090909091, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1444.0, "min": 1063.0, "max": 1469.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.254545454545454, "min": 24.15909090909091, "max": 26.70909090909091, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1444.0, "min": 1063.0, "max": 1469.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744794992", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744795606" }, "total": 613.9766473329998, "count": 1, "self": 0.42636831499976324, "children": { "run_training.setup": { "total": 0.020260753000002296, "count": 1, "self": 0.020260753000002296 }, "TrainerController.start_learning": { "total": 613.5300182650001, "count": 1, "self": 0.4642594350075342, "children": { "TrainerController._reset_env": { "total": 2.0167149079998126, "count": 1, "self": 2.0167149079998126 }, "TrainerController.advance": { "total": 610.9616803559927, "count": 27264, "self": 0.48663881705647327, "children": { "env_step": { "total": 430.33856703599736, "count": 27264, "self": 328.26124668298166, "children": { "SubprocessEnvManager._take_step": { "total": 101.78582413599838, "count": 27264, "self": 1.8210247900153718, "children": { "TorchPolicy.evaluate": { "total": 99.96479934598301, "count": 27264, "self": 99.96479934598301 } } }, "workers": { "total": 0.2914962170173112, "count": 27264, "self": 0.0, "children": { "worker_root": { "total": 611.5841291410438, "count": 27264, "is_parallel": true, "self": 322.83378687806794, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021035359998222702, "count": 1, "is_parallel": true, "self": 0.0006520209999507642, "children": { "_process_rank_one_or_two_observation": { "total": 0.001451514999871506, "count": 10, "is_parallel": true, "self": 0.001451514999871506 } } }, "UnityEnvironment.step": { "total": 0.03561748800007081, "count": 1, "is_parallel": true, "self": 0.0005518640000445885, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037792900002386887, "count": 1, "is_parallel": true, "self": 0.00037792900002386887 }, "communicator.exchange": { "total": 0.03293755599997894, "count": 1, "is_parallel": true, "self": 0.03293755599997894 }, "steps_from_proto": { "total": 0.0017501390000234096, "count": 1, "is_parallel": true, "self": 0.00032810400057314837, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014220349994502612, "count": 10, "is_parallel": true, "self": 0.0014220349994502612 } } } } } } }, "UnityEnvironment.step": { "total": 288.7503422629759, "count": 27263, "is_parallel": true, "self": 13.965315862040825, "children": { "UnityEnvironment._generate_step_input": { "total": 8.04956736399049, "count": 27263, "is_parallel": true, "self": 8.04956736399049 }, "communicator.exchange": { "total": 221.67666052095365, "count": 27263, "is_parallel": true, "self": 221.67666052095365 }, "steps_from_proto": { "total": 45.05879851599093, "count": 27263, "is_parallel": true, "self": 7.833092072944737, "children": { "_process_rank_one_or_two_observation": { "total": 37.22570644304619, "count": 272630, "is_parallel": true, "self": 37.22570644304619 } } } } } } } } } } }, "trainer_advance": { "total": 180.13647450293888, "count": 27264, "self": 0.5512165378934242, "children": { "process_trajectory": { "total": 38.8073247140469, "count": 27264, "self": 38.23470988604777, "children": { "RLTrainer._checkpoint": { "total": 0.5726148279991321, "count": 6, "self": 0.5726148279991321 } } }, "_update_policy": { "total": 140.77793325099856, "count": 136, "self": 56.05927576300928, "children": { "TorchPPOOptimizer.update": { "total": 84.71865748798928, "count": 6933, "self": 84.71865748798928 } } } } } } }, "trainer_threads": { "total": 1.235000127053354e-06, "count": 1, "self": 1.235000127053354e-06 }, "TrainerController._save_models": { "total": 0.08736233099989477, "count": 1, "self": 0.0010968009996759065, "children": { "RLTrainer._checkpoint": { "total": 0.08626553000021886, "count": 1, "self": 0.08626553000021886 } } } } } } }