{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8691378831863403, "min": 0.8691378831863403, "max": 2.8486580848693848, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8288.9677734375, "min": 8288.9677734375, "max": 29141.771484375, "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": 12.493813514709473, "min": 0.4192144274711609, "max": 12.493813514709473, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2436.293701171875, "min": 81.32759857177734, "max": 2535.48974609375, "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": 0.07289650142575185, "min": 0.0649851690438535, "max": 0.07340353793297967, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2915860057030074, "min": 0.26553098077648407, "max": 0.36701768966489834, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19736389633195073, "min": 0.13440494327897243, "max": 0.2738260792166579, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7894555853278029, "min": 0.5376197731158897, "max": 1.3691303960832895, "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": 24.545454545454547, "min": 3.7045454545454546, "max": 24.70909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1080.0, "min": 163.0, "max": 1359.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.545454545454547, "min": 3.7045454545454546, "max": 24.70909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1080.0, "min": 163.0, "max": 1359.0, "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": "1709830504", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709830985" }, "total": 480.95088157500004, "count": 1, "self": 0.49137071800009835, "children": { "run_training.setup": { "total": 0.05653481199999533, "count": 1, "self": 0.05653481199999533 }, "TrainerController.start_learning": { "total": 480.40297604499995, "count": 1, "self": 0.6183012009948925, "children": { "TrainerController._reset_env": { "total": 2.7245755779999854, "count": 1, "self": 2.7245755779999854 }, "TrainerController.advance": { "total": 476.9521784870051, "count": 18198, "self": 0.29738759899760225, "children": { "env_step": { "total": 476.6547908880075, "count": 18198, "self": 309.39840186499987, "children": { "SubprocessEnvManager._take_step": { "total": 166.9416884190049, "count": 18198, "self": 1.5666131800218182, "children": { "TorchPolicy.evaluate": { "total": 165.37507523898307, "count": 18198, "self": 165.37507523898307 } } }, "workers": { "total": 0.3147006040027236, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 479.1840317760102, "count": 18198, "is_parallel": true, "self": 238.91392804400812, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005445530999963921, "count": 1, "is_parallel": true, "self": 0.003926769999907265, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015187610000566565, "count": 10, "is_parallel": true, "self": 0.0015187610000566565 } } }, "UnityEnvironment.step": { "total": 0.03831589399999302, "count": 1, "is_parallel": true, "self": 0.000778632999868023, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004499010000245107, "count": 1, "is_parallel": true, "self": 0.0004499010000245107 }, "communicator.exchange": { "total": 0.03494914100008373, "count": 1, "is_parallel": true, "self": 0.03494914100008373 }, "steps_from_proto": { "total": 0.002138219000016761, "count": 1, "is_parallel": true, "self": 0.0003963950000525074, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017418239999642537, "count": 10, "is_parallel": true, "self": 0.0017418239999642537 } } } } } } }, "UnityEnvironment.step": { "total": 240.2701037320021, "count": 18197, "is_parallel": true, "self": 10.99444467400167, "children": { "UnityEnvironment._generate_step_input": { "total": 5.815296274004822, "count": 18197, "is_parallel": true, "self": 5.815296274004822 }, "communicator.exchange": { "total": 186.66911237000113, "count": 18197, "is_parallel": true, "self": 186.66911237000113 }, "steps_from_proto": { "total": 36.791250413994476, "count": 18197, "is_parallel": true, "self": 7.05775561697385, "children": { "_process_rank_one_or_two_observation": { "total": 29.733494797020626, "count": 181970, "is_parallel": true, "self": 29.733494797020626 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019586200005505816, "count": 1, "self": 0.00019586200005505816, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 470.78444519294703, "count": 717131, "is_parallel": true, "self": 16.01367996990075, "children": { "process_trajectory": { "total": 260.5544212700464, "count": 717131, "is_parallel": true, "self": 259.67152708604647, "children": { "RLTrainer._checkpoint": { "total": 0.8828941839999516, "count": 4, "is_parallel": true, "self": 0.8828941839999516 } } }, "_update_policy": { "total": 194.21634395299986, "count": 90, "is_parallel": true, "self": 57.12436340100237, "children": { "TorchPPOOptimizer.update": { "total": 137.0919805519975, "count": 4584, "is_parallel": true, "self": 137.0919805519975 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1077249169999277, "count": 1, "self": 0.0011986139999180523, "children": { "RLTrainer._checkpoint": { "total": 0.10652630300000965, "count": 1, "self": 0.10652630300000965 } } } } } } }