{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5489891171455383, "min": 0.5391390919685364, "max": 2.871898889541626, "count": 80 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5235.708984375, "min": 5150.0263671875, "max": 29442.70703125, "count": 80 }, "SnowballTarget.Step.mean": { "value": 799944.0, "min": 9952.0, "max": 799944.0, "count": 80 }, "SnowballTarget.Step.sum": { "value": 799944.0, "min": 9952.0, "max": 799944.0, "count": 80 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 2.8124263286590576, "min": 0.18106575310230255, "max": 2.8432693481445312, "count": 80 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 545.6107177734375, "min": 35.12675476074219, "max": 579.7280883789062, "count": 80 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 80 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 80 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06329568701895529, "min": 0.06084093116169599, "max": 0.080345641567107, "count": 80 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25318274807582114, "min": 0.24482596428567252, "max": 0.38094423504491504, "count": 80 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.11787128579967163, "min": 0.06393787799991996, "max": 0.16546367836349152, "count": 80 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4714851431986865, "min": 0.2557515119996798, "max": 0.8273183918174576, "count": 80 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.795599401499997e-06, "min": 1.795599401499997e-06, "max": 0.0002979705006765, "count": 80 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.182397605999988e-06, "min": 7.182397605999988e-06, "max": 0.0014712900095699996, "count": 80 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10059850000000001, "min": 0.10059850000000001, "max": 0.19932350000000001, "count": 80 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40239400000000003, "min": 0.40239400000000003, "max": 0.9904299999999999, "count": 80 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.9865149999999955e-05, "min": 3.9865149999999955e-05, "max": 0.00496624265, "count": 80 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00015946059999999982, "min": 0.00015946059999999982, "max": 0.024522457, "count": 80 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.34090909090909, "min": 3.3636363636363638, "max": 27.977272727272727, "count": 80 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1203.0, "min": 148.0, "max": 1530.0, "count": 80 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.34090909090909, "min": 3.3636363636363638, "max": 27.977272727272727, "count": 80 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1203.0, "min": 148.0, "max": 1530.0, "count": 80 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679807899", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1679809763" }, "total": 1863.9970559430003, "count": 1, "self": 0.426549027999954, "children": { "run_training.setup": { "total": 0.10871013500036497, "count": 1, "self": 0.10871013500036497 }, "TrainerController.start_learning": { "total": 1863.46179678, "count": 1, "self": 2.148878893890469, "children": { "TrainerController._reset_env": { "total": 7.154708530999869, "count": 1, "self": 7.154708530999869 }, "TrainerController.advance": { "total": 1854.0224671311094, "count": 72741, "self": 1.0669026770256096, "children": { "env_step": { "total": 1852.9555644540837, "count": 72741, "self": 1337.2729332359859, "children": { "SubprocessEnvManager._take_step": { "total": 514.6313742150601, "count": 72741, "self": 7.753451677128851, "children": { "TorchPolicy.evaluate": { "total": 506.8779225379312, "count": 72741, "self": 506.8779225379312 } } }, "workers": { "total": 1.0512570030377901, "count": 72741, "self": 0.0, "children": { "worker_root": { "total": 1857.5596979179281, "count": 72741, "is_parallel": true, "self": 857.4346367469634, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00507375500001217, "count": 1, "is_parallel": true, "self": 0.0007800979997227842, "children": { "_process_rank_one_or_two_observation": { "total": 0.004293657000289386, "count": 10, "is_parallel": true, "self": 0.004293657000289386 } } }, "UnityEnvironment.step": { "total": 0.03627138899992133, "count": 1, "is_parallel": true, "self": 0.0005611309993582836, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002928580001935188, "count": 1, "is_parallel": true, "self": 0.0002928580001935188 }, "communicator.exchange": { "total": 0.03341232900038449, "count": 1, "is_parallel": true, "self": 0.03341232900038449 }, "steps_from_proto": { "total": 0.002005070999985037, "count": 1, "is_parallel": true, "self": 0.0004571039985421521, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015479670014428848, "count": 10, "is_parallel": true, "self": 0.0015479670014428848 } } } } } } }, "UnityEnvironment.step": { "total": 1000.1250611709647, "count": 72740, "is_parallel": true, "self": 38.31052930991882, "children": { "UnityEnvironment._generate_step_input": { "total": 21.38248344702015, "count": 72740, "is_parallel": true, "self": 21.38248344702015 }, "communicator.exchange": { "total": 811.4177478579913, "count": 72740, "is_parallel": true, "self": 811.4177478579913 }, "steps_from_proto": { "total": 129.0143005560344, "count": 72740, "is_parallel": true, "self": 25.275552665940722, "children": { "_process_rank_one_or_two_observation": { "total": 103.73874789009369, "count": 727400, "is_parallel": true, "self": 103.73874789009369 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011620300028880592, "count": 1, "self": 0.00011620300028880592, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1840.4237638809386, "count": 1656742, "is_parallel": true, "self": 39.9274553978089, "children": { "process_trajectory": { "total": 1020.404982761132, "count": 1656742, "is_parallel": true, "self": 1016.1123666211315, "children": { "RLTrainer._checkpoint": { "total": 4.2926161400005185, "count": 16, "is_parallel": true, "self": 4.2926161400005185 } } }, "_update_policy": { "total": 780.0913257219977, "count": 363, "is_parallel": true, "self": 290.21580983597596, "children": { "TorchPPOOptimizer.update": { "total": 489.87551588602173, "count": 18504, "is_parallel": true, "self": 489.87551588602173 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1356260210000073, "count": 1, "self": 0.0012752570000884589, "children": { "RLTrainer._checkpoint": { "total": 0.13435076399991885, "count": 1, "self": 0.13435076399991885 } } } } } } }