{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9416508674621582, "min": 0.9403967261314392, "max": 2.8555054664611816, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9011.5986328125, "min": 9011.5986328125, "max": 29243.23046875, "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": 12.593409538269043, "min": 0.33124324679374695, "max": 12.593409538269043, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2455.71484375, "min": 64.26119232177734, "max": 2526.06640625, "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": 0.06574329855856394, "min": 0.06213809438290185, "max": 0.07476429355992165, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26297319423425575, "min": 0.2485523775316074, "max": 0.37382146779960823, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19034470573944207, "min": 0.13596110519218058, "max": 0.28083529314574074, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7613788229577683, "min": 0.5438444207687223, "max": 1.4041764657287037, "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": 24.84090909090909, "min": 4.0227272727272725, "max": 24.927272727272726, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1093.0, "min": 177.0, "max": 1371.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.84090909090909, "min": 4.0227272727272725, "max": 24.927272727272726, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1093.0, "min": 177.0, "max": 1371.0, "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": "1697819474", "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": "1697819948" }, "total": 473.9667026520001, "count": 1, "self": 0.43633845499994095, "children": { "run_training.setup": { "total": 0.04746784800011028, "count": 1, "self": 0.04746784800011028 }, "TrainerController.start_learning": { "total": 473.48289634900004, "count": 1, "self": 0.5242576769971947, "children": { "TrainerController._reset_env": { "total": 8.96595340400006, "count": 1, "self": 8.96595340400006 }, "TrainerController.advance": { "total": 463.908021120003, "count": 18201, "self": 0.2681617860055212, "children": { "env_step": { "total": 463.6398593339975, "count": 18201, "self": 317.2370287559843, "children": { "SubprocessEnvManager._take_step": { "total": 146.12952674300823, "count": 18201, "self": 1.4437907810130355, "children": { "TorchPolicy.evaluate": { "total": 144.6857359619952, "count": 18201, "self": 144.6857359619952 } } }, "workers": { "total": 0.273303835004981, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 472.2451903809888, "count": 18201, "is_parallel": true, "self": 233.03984700098704, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005872189999990951, "count": 1, "is_parallel": true, "self": 0.004337493999969411, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015346960000215404, "count": 10, "is_parallel": true, "self": 0.0015346960000215404 } } }, "UnityEnvironment.step": { "total": 0.03495165799995448, "count": 1, "is_parallel": true, "self": 0.000382695999974203, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003904300000385774, "count": 1, "is_parallel": true, "self": 0.0003904300000385774 }, "communicator.exchange": { "total": 0.03300047200002609, "count": 1, "is_parallel": true, "self": 0.03300047200002609 }, "steps_from_proto": { "total": 0.0011780599999156038, "count": 1, "is_parallel": true, "self": 0.000291747000005671, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008863129999099328, "count": 10, "is_parallel": true, "self": 0.0008863129999099328 } } } } } } }, "UnityEnvironment.step": { "total": 239.20534338000175, "count": 18200, "is_parallel": true, "self": 10.675397339022197, "children": { "UnityEnvironment._generate_step_input": { "total": 5.356253338988154, "count": 18200, "is_parallel": true, "self": 5.356253338988154 }, "communicator.exchange": { "total": 188.95317396098994, "count": 18200, "is_parallel": true, "self": 188.95317396098994 }, "steps_from_proto": { "total": 34.220518741001456, "count": 18200, "is_parallel": true, "self": 6.399243420967196, "children": { "_process_rank_one_or_two_observation": { "total": 27.82127532003426, "count": 182000, "is_parallel": true, "self": 27.82127532003426 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012959999980921566, "count": 1, "self": 0.00012959999980921566, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 460.061216293955, "count": 475962, "is_parallel": true, "self": 10.32857170092484, "children": { "process_trajectory": { "total": 259.7901070780297, "count": 475962, "is_parallel": true, "self": 259.23690721202956, "children": { "RLTrainer._checkpoint": { "total": 0.5531998660001136, "count": 4, "is_parallel": true, "self": 0.5531998660001136 } } }, "_update_policy": { "total": 189.94253751500048, "count": 90, "is_parallel": true, "self": 59.186408164, "children": { "TorchPPOOptimizer.update": { "total": 130.75612935100048, "count": 4587, "is_parallel": true, "self": 130.75612935100048 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08453454799996507, "count": 1, "self": 0.0009417629999006749, "children": { "RLTrainer._checkpoint": { "total": 0.0835927850000644, "count": 1, "self": 0.0835927850000644 } } } } } } }