{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9940366148948669, "min": 0.9940366148948669, "max": 2.8748860359191895, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9480.126953125, "min": 9480.126953125, "max": 29441.70703125, "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": 11.956221580505371, "min": 0.3115452229976654, "max": 11.956221580505371, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2331.463134765625, "min": 60.43977355957031, "max": 2419.692626953125, "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": 0.07123493834603556, "min": 0.060121397685411374, "max": 0.07219560799899673, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28493975338414224, "min": 0.2404855907416455, "max": 0.35559002817664054, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19119824136735178, "min": 0.09855278322413819, "max": 0.29750193085740595, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7647929654694071, "min": 0.39421113289655274, "max": 1.3086565084317152, "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": 23.636363636363637, "min": 2.6363636363636362, "max": 23.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1040.0, "min": 116.0, "max": 1290.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.636363636363637, "min": 2.6363636363636362, "max": 23.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1040.0, "min": 116.0, "max": 1290.0, "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": "1678488017", "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", "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": "1678488467" }, "total": 449.9183872699999, "count": 1, "self": 0.7359138759998132, "children": { "run_training.setup": { "total": 0.10957124700007626, "count": 1, "self": 0.10957124700007626 }, "TrainerController.start_learning": { "total": 449.07290214700004, "count": 1, "self": 0.49724402299432313, "children": { "TrainerController._reset_env": { "total": 9.436892230000012, "count": 1, "self": 9.436892230000012 }, "TrainerController.advance": { "total": 438.9474600590056, "count": 18201, "self": 0.25265621398818894, "children": { "env_step": { "total": 438.6948038450174, "count": 18201, "self": 319.21209501802593, "children": { "SubprocessEnvManager._take_step": { "total": 119.23012178600379, "count": 18201, "self": 2.5849632369986466, "children": { "TorchPolicy.evaluate": { "total": 116.64515854900515, "count": 18201, "self": 116.64515854900515 } } }, "workers": { "total": 0.2525870409876916, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 447.6864041780143, "count": 18201, "is_parallel": true, "self": 215.29449341101292, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005468264000001, "count": 1, "is_parallel": true, "self": 0.003895180999961667, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015730830000393325, "count": 10, "is_parallel": true, "self": 0.0015730830000393325 } } }, "UnityEnvironment.step": { "total": 0.04003489999990961, "count": 1, "is_parallel": true, "self": 0.0004745080000247981, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032555899997532833, "count": 1, "is_parallel": true, "self": 0.00032555899997532833 }, "communicator.exchange": { "total": 0.037515664000011384, "count": 1, "is_parallel": true, "self": 0.037515664000011384 }, "steps_from_proto": { "total": 0.001719168999898102, "count": 1, "is_parallel": true, "self": 0.00034721199983778206, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013719570000603198, "count": 10, "is_parallel": true, "self": 0.0013719570000603198 } } } } } } }, "UnityEnvironment.step": { "total": 232.39191076700138, "count": 18200, "is_parallel": true, "self": 9.300932250994038, "children": { "UnityEnvironment._generate_step_input": { "total": 4.999884784995743, "count": 18200, "is_parallel": true, "self": 4.999884784995743 }, "communicator.exchange": { "total": 188.42808561301013, "count": 18200, "is_parallel": true, "self": 188.42808561301013 }, "steps_from_proto": { "total": 29.66300811800147, "count": 18200, "is_parallel": true, "self": 5.819285871007196, "children": { "_process_rank_one_or_two_observation": { "total": 23.843722246994275, "count": 182000, "is_parallel": true, "self": 23.843722246994275 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001022920000650629, "count": 1, "self": 0.0001022920000650629, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 435.71427329001494, "count": 383537, "is_parallel": true, "self": 9.2703491920455, "children": { "process_trajectory": { "total": 240.32447715796934, "count": 383537, "is_parallel": true, "self": 239.24052463696944, "children": { "RLTrainer._checkpoint": { "total": 1.083952520999901, "count": 4, "is_parallel": true, "self": 1.083952520999901 } } }, "_update_policy": { "total": 186.1194469400001, "count": 90, "is_parallel": true, "self": 72.69556645900286, "children": { "TorchPPOOptimizer.update": { "total": 113.42388048099724, "count": 4587, "is_parallel": true, "self": 113.42388048099724 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19120354300002873, "count": 1, "self": 0.0010744680000698281, "children": { "RLTrainer._checkpoint": { "total": 0.1901290749999589, "count": 1, "self": 0.1901290749999589 } } } } } } }