{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2237701416015625, "min": 1.2237701416015625, "max": 2.869323968887329, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11630.7109375, "min": 11630.7109375, "max": 29290.05859375, "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": 4.0057597160339355, "min": 0.10311666131019592, "max": 4.0057597160339355, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 781.1231689453125, "min": 20.0046329498291, "max": 793.1399536132812, "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.Environment.CumulativeReward.mean": { "value": 23.75, "min": 3.5681818181818183, "max": 23.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1045.0, "min": 157.0, "max": 1291.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.75, "min": 3.5681818181818183, "max": 23.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1045.0, "min": 157.0, "max": 1291.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06782803665936465, "min": 0.06515288824501861, "max": 0.07488476704544583, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.1356560733187293, "min": 0.13030577649003722, "max": 0.21634183238410354, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17946520139846733, "min": 0.0857328301293978, "max": 0.20264035074368997, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.35893040279693467, "min": 0.1714656602587956, "max": 0.5778850038919379, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.1440978560000015e-06, "min": 2.1440978560000015e-06, "max": 9.674400325600001e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.288195712000003e-06, "min": 4.288195712000003e-06, "max": 0.000247332052668, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10214399999999998, "min": 0.10214399999999998, "max": 0.196744, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20428799999999997, "min": 0.20428799999999997, "max": 0.547332, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001169856000000001, "min": 0.0001169856000000001, "max": 0.0048375256, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0002339712000000002, "min": 0.0002339712000000002, "max": 0.0123718668, "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": "1738328558", "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=SnowballTarget0 --no-graphics", "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": "1738329222" }, "total": 664.4085103199996, "count": 1, "self": 0.4251312609994784, "children": { "run_training.setup": { "total": 0.020845822999945085, "count": 1, "self": 0.020845822999945085 }, "TrainerController.start_learning": { "total": 663.9625332360001, "count": 1, "self": 0.33206875592804863, "children": { "TrainerController._reset_env": { "total": 2.0098319909993734, "count": 1, "self": 2.0098319909993734 }, "TrainerController.advance": { "total": 661.4998802690725, "count": 18192, "self": 0.37118673028544436, "children": { "env_step": { "total": 296.9512954838956, "count": 18192, "self": 224.30317155377998, "children": { "SubprocessEnvManager._take_step": { "total": 72.44837594802812, "count": 18192, "self": 1.221809745007704, "children": { "TorchPolicy.evaluate": { "total": 71.22656620302041, "count": 18192, "self": 71.22656620302041 } } }, "workers": { "total": 0.19974798208750144, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 662.5666524800426, "count": 18192, "is_parallel": true, "self": 465.82781918897945, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021633480000673444, "count": 1, "is_parallel": true, "self": 0.0006412849998014281, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015220630002659163, "count": 10, "is_parallel": true, "self": 0.0015220630002659163 } } }, "UnityEnvironment.step": { "total": 0.03351324800041766, "count": 1, "is_parallel": true, "self": 0.0005717780004488304, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043470499986142386, "count": 1, "is_parallel": true, "self": 0.00043470499986142386 }, "communicator.exchange": { "total": 0.030688670000017737, "count": 1, "is_parallel": true, "self": 0.030688670000017737 }, "steps_from_proto": { "total": 0.00181809500008967, "count": 1, "is_parallel": true, "self": 0.0003682970000227215, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014497980000669486, "count": 10, "is_parallel": true, "self": 0.0014497980000669486 } } } } } } }, "UnityEnvironment.step": { "total": 196.7388332910632, "count": 18191, "is_parallel": true, "self": 9.423318505999305, "children": { "UnityEnvironment._generate_step_input": { "total": 5.146944604024611, "count": 18191, "is_parallel": true, "self": 5.146944604024611 }, "communicator.exchange": { "total": 151.8282429579449, "count": 18191, "is_parallel": true, "self": 151.8282429579449 }, "steps_from_proto": { "total": 30.34032722309439, "count": 18191, "is_parallel": true, "self": 5.292450126218682, "children": { "_process_rank_one_or_two_observation": { "total": 25.04787709687571, "count": 181910, "is_parallel": true, "self": 25.04787709687571 } } } } } } } } } } }, "trainer_advance": { "total": 364.17739805489146, "count": 18192, "self": 0.3921815639059787, "children": { "process_trajectory": { "total": 28.94245231698642, "count": 18192, "self": 28.227960468987476, "children": { "RLTrainer._checkpoint": { "total": 0.7144918479989428, "count": 4, "self": 0.7144918479989428 } } }, "_update_policy": { "total": 334.84276417399906, "count": 45, "self": 124.78452919807569, "children": { "TorchPPOOptimizer.update": { "total": 210.05823497592337, "count": 15290, "self": 210.05823497592337 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.12075127400021302, "count": 1, "self": 0.001273830000172893, "children": { "RLTrainer._checkpoint": { "total": 0.11947744400004012, "count": 1, "self": 0.11947744400004012 } } } } } } }