{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9611787796020508, "min": 0.9611787796020508, "max": 2.867449998855591, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9219.626953125, "min": 9219.626953125, "max": 29365.5546875, "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": 12.7700834274292, "min": 0.41108036041259766, "max": 12.801994323730469, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2490.166259765625, "min": 79.74958801269531, "max": 2611.60693359375, "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": 0.06710186744629597, "min": 0.06421257007319832, "max": 0.07501877670509596, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26840746978518387, "min": 0.2568502802927933, "max": 0.3583485061261693, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20030220638157106, "min": 0.12611407209667103, "max": 0.29629942517654567, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8012088255262843, "min": 0.5044562883866841, "max": 1.4814971258827283, "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": 25.15909090909091, "min": 3.409090909090909, "max": 25.327272727272728, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 150.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.409090909090909, "max": 25.327272727272728, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 150.0, "max": 1393.0, "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": "1716462798", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716463263" }, "total": 464.72758715299994, "count": 1, "self": 0.4340237789998582, "children": { "run_training.setup": { "total": 0.05785653300006288, "count": 1, "self": 0.05785653300006288 }, "TrainerController.start_learning": { "total": 464.235706841, "count": 1, "self": 0.594862553985763, "children": { "TrainerController._reset_env": { "total": 3.3487922199999502, "count": 1, "self": 3.3487922199999502 }, "TrainerController.advance": { "total": 460.20079718701436, "count": 18208, "self": 0.27639272401165726, "children": { "env_step": { "total": 459.9244044630027, "count": 18208, "self": 300.8360878149971, "children": { "SubprocessEnvManager._take_step": { "total": 158.52237199101285, "count": 18208, "self": 1.5326046410168601, "children": { "TorchPolicy.evaluate": { "total": 156.989767349996, "count": 18208, "self": 156.989767349996 } } }, "workers": { "total": 0.5659446569927695, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 462.88441823501194, "count": 18208, "is_parallel": true, "self": 233.6339825810171, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005589761000010185, "count": 1, "is_parallel": true, "self": 0.003813018999721862, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017767420002883227, "count": 10, "is_parallel": true, "self": 0.0017767420002883227 } } }, "UnityEnvironment.step": { "total": 0.07516639599998598, "count": 1, "is_parallel": true, "self": 0.0006815929999675063, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004245769999897675, "count": 1, "is_parallel": true, "self": 0.0004245769999897675 }, "communicator.exchange": { "total": 0.07181303699996988, "count": 1, "is_parallel": true, "self": 0.07181303699996988 }, "steps_from_proto": { "total": 0.0022471890000588246, "count": 1, "is_parallel": true, "self": 0.00044732099991051655, "children": { "_process_rank_one_or_two_observation": { "total": 0.001799868000148308, "count": 10, "is_parallel": true, "self": 0.001799868000148308 } } } } } } }, "UnityEnvironment.step": { "total": 229.25043565399483, "count": 18207, "is_parallel": true, "self": 10.374262145011357, "children": { "UnityEnvironment._generate_step_input": { "total": 5.601206244010655, "count": 18207, "is_parallel": true, "self": 5.601206244010655 }, "communicator.exchange": { "total": 177.99398461898454, "count": 18207, "is_parallel": true, "self": 177.99398461898454 }, "steps_from_proto": { "total": 35.280982645988274, "count": 18207, "is_parallel": true, "self": 6.605236749998198, "children": { "_process_rank_one_or_two_observation": { "total": 28.675745895990076, "count": 182070, "is_parallel": true, "self": 28.675745895990076 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014598000007026712, "count": 1, "self": 0.00014598000007026712, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.42453250685844, "count": 681179, "is_parallel": true, "self": 14.566836952941571, "children": { "process_trajectory": { "total": 252.47026952991644, "count": 681179, "is_parallel": true, "self": 251.48068578391656, "children": { "RLTrainer._checkpoint": { "total": 0.9895837459998802, "count": 4, "is_parallel": true, "self": 0.9895837459998802 } } }, "_update_policy": { "total": 187.38742602400043, "count": 90, "is_parallel": true, "self": 61.328258073987286, "children": { "TorchPPOOptimizer.update": { "total": 126.05916795001315, "count": 4587, "is_parallel": true, "self": 126.05916795001315 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09110889999988103, "count": 1, "self": 0.000902054999869506, "children": { "RLTrainer._checkpoint": { "total": 0.09020684500001153, "count": 1, "self": 0.09020684500001153 } } } } } } }