{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9100767970085144, "min": 0.8905326724052429, "max": 2.8647546768188477, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8689.4130859375, "min": 8689.4130859375, "max": 29400.9765625, "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": 12.955817222595215, "min": 0.29277995228767395, "max": 12.984021186828613, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.38427734375, "min": 56.79930877685547, "max": 2648.740234375, "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": 0.06888256136638424, "min": 0.06365613901768538, "max": 0.0722638340241746, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27553024546553695, "min": 0.26703546619654506, "max": 0.35997121352817224, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20296008475855284, "min": 0.10602139343288454, "max": 0.29962344336159086, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8118403390342114, "min": 0.42408557373153816, "max": 1.366826533686881, "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": 25.15909090909091, "min": 3.022727272727273, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 133.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.022727272727273, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 133.0, "max": 1403.0, "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": "1691618773", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691619361" }, "total": 587.807704712, "count": 1, "self": 0.48324040400007107, "children": { "run_training.setup": { "total": 0.04933895799996435, "count": 1, "self": 0.04933895799996435 }, "TrainerController.start_learning": { "total": 587.27512535, "count": 1, "self": 0.7393187349955497, "children": { "TrainerController._reset_env": { "total": 6.227064918999986, "count": 1, "self": 6.227064918999986 }, "TrainerController.advance": { "total": 580.1402146870045, "count": 18202, "self": 0.3868223420029153, "children": { "env_step": { "total": 579.7533923450015, "count": 18202, "self": 425.2851150140023, "children": { "SubprocessEnvManager._take_step": { "total": 154.09227691199288, "count": 18202, "self": 2.430427448984176, "children": { "TorchPolicy.evaluate": { "total": 151.6618494630087, "count": 18202, "self": 151.6618494630087 } } }, "workers": { "total": 0.3760004190063455, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 585.1947075329915, "count": 18202, "is_parallel": true, "self": 267.27940483500066, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005879564999986542, "count": 1, "is_parallel": true, "self": 0.004208035999909043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016715290000774985, "count": 10, "is_parallel": true, "self": 0.0016715290000774985 } } }, "UnityEnvironment.step": { "total": 0.06492515899998352, "count": 1, "is_parallel": true, "self": 0.0007368400000018482, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004910509999831447, "count": 1, "is_parallel": true, "self": 0.0004910509999831447 }, "communicator.exchange": { "total": 0.06122663799999373, "count": 1, "is_parallel": true, "self": 0.06122663799999373 }, "steps_from_proto": { "total": 0.002470630000004803, "count": 1, "is_parallel": true, "self": 0.00042862500004048343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020420049999643197, "count": 10, "is_parallel": true, "self": 0.0020420049999643197 } } } } } } }, "UnityEnvironment.step": { "total": 317.91530269799085, "count": 18201, "is_parallel": true, "self": 13.555733604988177, "children": { "UnityEnvironment._generate_step_input": { "total": 6.674029255997482, "count": 18201, "is_parallel": true, "self": 6.674029255997482 }, "communicator.exchange": { "total": 251.9585286190029, "count": 18201, "is_parallel": true, "self": 251.9585286190029 }, "steps_from_proto": { "total": 45.7270112180023, "count": 18201, "is_parallel": true, "self": 8.684109520979916, "children": { "_process_rank_one_or_two_observation": { "total": 37.04290169702239, "count": 182010, "is_parallel": true, "self": 37.04290169702239 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015189999999165593, "count": 1, "self": 0.00015189999999165593, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 575.3112012770093, "count": 547216, "is_parallel": true, "self": 13.315842596026187, "children": { "process_trajectory": { "total": 316.74073894798346, "count": 547216, "is_parallel": true, "self": 314.64044264798355, "children": { "RLTrainer._checkpoint": { "total": 2.1002962999999113, "count": 4, "is_parallel": true, "self": 2.1002962999999113 } } }, "_update_policy": { "total": 245.25461973299969, "count": 90, "is_parallel": true, "self": 97.11929791500006, "children": { "TorchPPOOptimizer.update": { "total": 148.13532181799962, "count": 4587, "is_parallel": true, "self": 148.13532181799962 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1683751090000669, "count": 1, "self": 0.0009761460000845545, "children": { "RLTrainer._checkpoint": { "total": 0.16739896299998236, "count": 1, "self": 0.16739896299998236 } } } } } } }