{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9645881056785583, "min": 0.9645881056785583, "max": 2.8631346225738525, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9231.1083984375, "min": 9231.1083984375, "max": 29321.361328125, "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": 12.710789680480957, "min": 0.41503843665122986, "max": 12.751395225524902, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2478.60400390625, "min": 80.5174560546875, "max": 2601.28466796875, "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": 0.06762708881095639, "min": 0.06264751766624006, "max": 0.0732921762825629, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27050835524382555, "min": 0.25059007066496025, "max": 0.358468279628284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18999936343992457, "min": 0.13599461400721624, "max": 0.29469047808179666, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7599974537596983, "min": 0.543978456028865, "max": 1.4558063795169196, "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": 24.863636363636363, "min": 4.136363636363637, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1094.0, "min": 182.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.863636363636363, "min": 4.136363636363637, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1094.0, "min": 182.0, "max": 1388.0, "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": "1695907805", "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 --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695908292" }, "total": 487.81525632399996, "count": 1, "self": 0.4241840219999631, "children": { "run_training.setup": { "total": 0.05448181899998872, "count": 1, "self": 0.05448181899998872 }, "TrainerController.start_learning": { "total": 487.336590483, "count": 1, "self": 0.5503704469909962, "children": { "TrainerController._reset_env": { "total": 4.933057276999989, "count": 1, "self": 4.933057276999989 }, "TrainerController.advance": { "total": 481.707295400009, "count": 18202, "self": 0.26153175500553516, "children": { "env_step": { "total": 481.44576364500347, "count": 18202, "self": 348.5702667549957, "children": { "SubprocessEnvManager._take_step": { "total": 132.59862181099595, "count": 18202, "self": 1.7356725590004771, "children": { "TorchPolicy.evaluate": { "total": 130.86294925199547, "count": 18202, "self": 130.86294925199547 } } }, "workers": { "total": 0.27687507901180197, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 485.74802399100497, "count": 18202, "is_parallel": true, "self": 233.40045177801642, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005842251999979453, "count": 1, "is_parallel": true, "self": 0.004330151999852205, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015121000001272478, "count": 10, "is_parallel": true, "self": 0.0015121000001272478 } } }, "UnityEnvironment.step": { "total": 0.11493170599999303, "count": 1, "is_parallel": true, "self": 0.0006491649999134097, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005090390000077605, "count": 1, "is_parallel": true, "self": 0.0005090390000077605 }, "communicator.exchange": { "total": 0.10680287800005317, "count": 1, "is_parallel": true, "self": 0.10680287800005317 }, "steps_from_proto": { "total": 0.006970624000018688, "count": 1, "is_parallel": true, "self": 0.0027790719999529756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0041915520000657125, "count": 10, "is_parallel": true, "self": 0.0041915520000657125 } } } } } } }, "UnityEnvironment.step": { "total": 252.34757221298855, "count": 18201, "is_parallel": true, "self": 10.267069578972041, "children": { "UnityEnvironment._generate_step_input": { "total": 5.6640785680028785, "count": 18201, "is_parallel": true, "self": 5.6640785680028785 }, "communicator.exchange": { "total": 200.1329038630014, "count": 18201, "is_parallel": true, "self": 200.1329038630014 }, "steps_from_proto": { "total": 36.283520203012245, "count": 18201, "is_parallel": true, "self": 6.713441203049911, "children": { "_process_rank_one_or_two_observation": { "total": 29.570078999962334, "count": 182010, "is_parallel": true, "self": 29.570078999962334 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010535100000197417, "count": 1, "self": 0.00010535100000197417, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 477.88723492595454, "count": 457910, "is_parallel": true, "self": 10.239880598954528, "children": { "process_trajectory": { "total": 260.480925028, "count": 457910, "is_parallel": true, "self": 259.69715035900003, "children": { "RLTrainer._checkpoint": { "total": 0.7837746689999676, "count": 4, "is_parallel": true, "self": 0.7837746689999676 } } }, "_update_policy": { "total": 207.16642929900001, "count": 90, "is_parallel": true, "self": 80.54774998400171, "children": { "TorchPPOOptimizer.update": { "total": 126.6186793149983, "count": 4587, "is_parallel": true, "self": 126.6186793149983 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1457620080000197, "count": 1, "self": 0.0008865940000077899, "children": { "RLTrainer._checkpoint": { "total": 0.14487541400001192, "count": 1, "self": 0.14487541400001192 } } } } } } }