{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8279334902763367, "min": 0.8279334902763367, "max": 2.8590214252471924, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7896.001953125, "min": 7896.001953125, "max": 29279.23828125, "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": 12.960752487182617, "min": 0.2753119170665741, "max": 12.960752487182617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2527.3466796875, "min": 53.4105110168457, "max": 2642.76611328125, "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": 0.07264678573390519, "min": 0.06446490807506694, "max": 0.07321259986024861, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29058714293562077, "min": 0.26223109220311513, "max": 0.3660629993012431, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19491095789799504, "min": 0.12156432431291643, "max": 0.27539325730473385, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7796438315919801, "min": 0.4862572972516657, "max": 1.3769662865236691, "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": 25.045454545454547, "min": 3.340909090909091, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 147.0, "max": 1421.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.340909090909091, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 147.0, "max": 1421.0, "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": "1674035472", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674035911" }, "total": 438.928908297, "count": 1, "self": 0.38872646999993776, "children": { "run_training.setup": { "total": 0.1035128830000076, "count": 1, "self": 0.1035128830000076 }, "TrainerController.start_learning": { "total": 438.4366689440001, "count": 1, "self": 0.5348161190139535, "children": { "TrainerController._reset_env": { "total": 9.630275627999936, "count": 1, "self": 9.630275627999936 }, "TrainerController.advance": { "total": 428.14202194398615, "count": 18201, "self": 0.263697386955414, "children": { "env_step": { "total": 427.87832455703074, "count": 18201, "self": 280.07090272503035, "children": { "SubprocessEnvManager._take_step": { "total": 147.54148002299723, "count": 18201, "self": 1.4011753590028775, "children": { "TorchPolicy.evaluate": { "total": 146.14030466399436, "count": 18201, "self": 33.370133937987475, "children": { "TorchPolicy.sample_actions": { "total": 112.77017072600688, "count": 18201, "self": 112.77017072600688 } } } } }, "workers": { "total": 0.26594180900315223, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 437.13143204398955, "count": 18201, "is_parallel": true, "self": 211.13834060199258, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005951294000055896, "count": 1, "is_parallel": true, "self": 0.003613513999994211, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023377800000616844, "count": 10, "is_parallel": true, "self": 0.0023377800000616844 } } }, "UnityEnvironment.step": { "total": 0.03607890499995392, "count": 1, "is_parallel": true, "self": 0.0006189309998489989, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033488300005046767, "count": 1, "is_parallel": true, "self": 0.00033488300005046767 }, "communicator.exchange": { "total": 0.033054273000061585, "count": 1, "is_parallel": true, "self": 0.033054273000061585 }, "steps_from_proto": { "total": 0.002070817999992869, "count": 1, "is_parallel": true, "self": 0.00047214399990025413, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015986740000926147, "count": 10, "is_parallel": true, "self": 0.0015986740000926147 } } } } } } }, "UnityEnvironment.step": { "total": 225.99309144199697, "count": 18200, "is_parallel": true, "self": 8.437238615998353, "children": { "UnityEnvironment._generate_step_input": { "total": 5.1142906330048845, "count": 18200, "is_parallel": true, "self": 5.1142906330048845 }, "communicator.exchange": { "total": 181.24482770000202, "count": 18200, "is_parallel": true, "self": 181.24482770000202 }, "steps_from_proto": { "total": 31.19673449299171, "count": 18200, "is_parallel": true, "self": 6.683066412021503, "children": { "_process_rank_one_or_two_observation": { "total": 24.513668080970206, "count": 182000, "is_parallel": true, "self": 24.513668080970206 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.3729000026360154e-05, "count": 1, "self": 4.3729000026360154e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 425.03856793990235, "count": 358624, "is_parallel": true, "self": 9.582208081875024, "children": { "process_trajectory": { "total": 245.9524048190283, "count": 358624, "is_parallel": true, "self": 245.2404350400284, "children": { "RLTrainer._checkpoint": { "total": 0.7119697789999009, "count": 4, "is_parallel": true, "self": 0.7119697789999009 } } }, "_update_policy": { "total": 169.50395503899904, "count": 90, "is_parallel": true, "self": 44.94844377999607, "children": { "TorchPPOOptimizer.update": { "total": 124.55551125900297, "count": 4587, "is_parallel": true, "self": 124.55551125900297 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12951152400000865, "count": 1, "self": 0.0008794579998721019, "children": { "RLTrainer._checkpoint": { "total": 0.12863206600013655, "count": 1, "self": 0.12863206600013655 } } } } } } }