{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8226407170295715, "min": 0.8026220798492432, "max": 2.8445403575897217, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7872.67138671875, "min": 7872.67138671875, "max": 29130.9375, "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": 12.589512825012207, "min": 0.17543712258338928, "max": 12.589512825012207, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2454.955078125, "min": 34.0348014831543, "max": 2553.1748046875, "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": 0.06571191077954626, "min": 0.06388546233539077, "max": 0.07430698846275097, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26284764311818504, "min": 0.2555418493415631, "max": 0.37153494231375483, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.25682572779410023, "min": 0.11142308088179276, "max": 0.27641374939212615, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.027302911176401, "min": 0.44569232352717103, "max": 1.3615016116231096, "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": 24.795454545454547, "min": 3.2045454545454546, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1091.0, "min": 141.0, "max": 1370.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.795454545454547, "min": 3.2045454545454546, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1091.0, "min": 141.0, "max": 1370.0, "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": "1702202483", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ../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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702203082" }, "total": 599.0347389509999, "count": 1, "self": 0.4979922489999353, "children": { "run_training.setup": { "total": 0.06515927899999951, "count": 1, "self": 0.06515927899999951 }, "TrainerController.start_learning": { "total": 598.471587423, "count": 1, "self": 0.7634159950017647, "children": { "TrainerController._reset_env": { "total": 3.901230385999952, "count": 1, "self": 3.901230385999952 }, "TrainerController.advance": { "total": 593.7047558199981, "count": 18201, "self": 0.38820602500095447, "children": { "env_step": { "total": 593.3165497949972, "count": 18201, "self": 404.8813685389861, "children": { "SubprocessEnvManager._take_step": { "total": 188.02534712800338, "count": 18201, "self": 1.9625154130069404, "children": { "TorchPolicy.evaluate": { "total": 186.06283171499643, "count": 18201, "self": 186.06283171499643 } } }, "workers": { "total": 0.4098341280076738, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 596.5738825609924, "count": 18201, "is_parallel": true, "self": 286.1041711049936, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004729753999981767, "count": 1, "is_parallel": true, "self": 0.003032173999997667, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016975799999841001, "count": 10, "is_parallel": true, "self": 0.0016975799999841001 } } }, "UnityEnvironment.step": { "total": 0.04354227300001412, "count": 1, "is_parallel": true, "self": 0.000716016000012587, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030122499998697094, "count": 1, "is_parallel": true, "self": 0.00030122499998697094 }, "communicator.exchange": { "total": 0.04031686400003309, "count": 1, "is_parallel": true, "self": 0.04031686400003309 }, "steps_from_proto": { "total": 0.0022081679999814696, "count": 1, "is_parallel": true, "self": 0.0004234070000279644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017847609999535052, "count": 10, "is_parallel": true, "self": 0.0017847609999535052 } } } } } } }, "UnityEnvironment.step": { "total": 310.4697114559988, "count": 18200, "is_parallel": true, "self": 13.03571384199887, "children": { "UnityEnvironment._generate_step_input": { "total": 6.899297766000359, "count": 18200, "is_parallel": true, "self": 6.899297766000359 }, "communicator.exchange": { "total": 246.62252043799248, "count": 18200, "is_parallel": true, "self": 246.62252043799248 }, "steps_from_proto": { "total": 43.91217941000707, "count": 18200, "is_parallel": true, "self": 8.699142504029226, "children": { "_process_rank_one_or_two_observation": { "total": 35.213036905977845, "count": 182000, "is_parallel": true, "self": 35.213036905977845 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001289599999836355, "count": 1, "self": 0.0001289599999836355, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 588.1170134540046, "count": 653274, "is_parallel": true, "self": 14.949635842016505, "children": { "process_trajectory": { "total": 336.6933899109876, "count": 653274, "is_parallel": true, "self": 336.04095296098745, "children": { "RLTrainer._checkpoint": { "total": 0.6524369500001512, "count": 4, "is_parallel": true, "self": 0.6524369500001512 } } }, "_update_policy": { "total": 236.47398770100045, "count": 90, "is_parallel": true, "self": 71.3498569520001, "children": { "TorchPPOOptimizer.update": { "total": 165.12413074900036, "count": 4587, "is_parallel": true, "self": 165.12413074900036 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10205626200013285, "count": 1, "self": 0.001340758000196729, "children": { "RLTrainer._checkpoint": { "total": 0.10071550399993612, "count": 1, "self": 0.10071550399993612 } } } } } } }