{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.807567834854126, "min": 2.807567834854126, "max": 2.8739852905273438, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 28968.484375, "min": 28968.484375, "max": 29432.482421875, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.2438939809799194, "min": 0.2919357717037201, "max": 1.2438939809799194, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 254.99826049804688, "min": 56.63554000854492, "max": 254.99826049804688, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06771399042781387, "min": 0.06771399042781387, "max": 0.0714372955381787, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3385699521390694, "min": 0.2857491821527148, "max": 0.3385699521390694, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19390695398929073, "min": 0.11701562528398034, "max": 0.19390695398929073, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9695347699464536, "min": 0.46806250113592135, "max": 0.9695347699464536, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 5.290909090909091, "min": 3.022727272727273, "max": 5.290909090909091, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 291.0, "min": 133.0, "max": 291.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.290909090909091, "min": 3.022727272727273, "max": 5.290909090909091, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 291.0, "min": 133.0, "max": 291.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679114819", "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": "1679114879" }, "total": 59.35834561899998, "count": 1, "self": 0.9208360659999926, "children": { "run_training.setup": { "total": 0.1376743430000147, "count": 1, "self": 0.1376743430000147 }, "TrainerController.start_learning": { "total": 58.29983520999997, "count": 1, "self": 0.10030118900067464, "children": { "TrainerController._reset_env": { "total": 9.269022235999955, "count": 1, "self": 9.269022235999955 }, "TrainerController.advance": { "total": 48.679397180999274, "count": 1870, "self": 0.032275204000939084, "children": { "env_step": { "total": 48.647121976998335, "count": 1870, "self": 35.29100767799963, "children": { "SubprocessEnvManager._take_step": { "total": 13.325656398999286, "count": 1870, "self": 0.17023340199847325, "children": { "TorchPolicy.evaluate": { "total": 13.155422997000812, "count": 1870, "self": 13.155422997000812 } } }, "workers": { "total": 0.03045789999941917, "count": 1870, "self": 0.0, "children": { "worker_root": { "total": 57.94905145899787, "count": 1870, "is_parallel": true, "self": 32.02168140799881, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007045734000030279, "count": 1, "is_parallel": true, "self": 0.005524985000079141, "children": { "_process_rank_one_or_two_observation": { "total": 0.001520748999951138, "count": 10, "is_parallel": true, "self": 0.001520748999951138 } } }, "UnityEnvironment.step": { "total": 0.09024463399998695, "count": 1, "is_parallel": true, "self": 0.0005722440000113238, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000346121999996285, "count": 1, "is_parallel": true, "self": 0.000346121999996285 }, "communicator.exchange": { "total": 0.0874664419999931, "count": 1, "is_parallel": true, "self": 0.0874664419999931 }, "steps_from_proto": { "total": 0.001859825999986242, "count": 1, "is_parallel": true, "self": 0.0003978289998940454, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014619970000921967, "count": 10, "is_parallel": true, "self": 0.0014619970000921967 } } } } } } }, "UnityEnvironment.step": { "total": 25.92737005099906, "count": 1869, "is_parallel": true, "self": 1.0352703279970683, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5810060680022957, "count": 1869, "is_parallel": true, "self": 0.5810060680022957 }, "communicator.exchange": { "total": 20.788842067999326, "count": 1869, "is_parallel": true, "self": 20.788842067999326 }, "steps_from_proto": { "total": 3.522251587000369, "count": 1869, "is_parallel": true, "self": 0.7610518300056697, "children": { "_process_rank_one_or_two_observation": { "total": 2.7611997569946993, "count": 18690, "is_parallel": true, "self": 2.7611997569946993 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003261130000282719, "count": 1, "self": 0.0003261130000282719, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 48.298664523995, "count": 47944, "is_parallel": true, "self": 1.1808888979892345, "children": { "process_trajectory": { "total": 27.353610033005793, "count": 47944, "is_parallel": true, "self": 27.353610033005793 }, "_update_policy": { "total": 19.764165592999973, "count": 9, "is_parallel": true, "self": 6.974977577000232, "children": { "TorchPPOOptimizer.update": { "total": 12.789188015999741, "count": 456, "is_parallel": true, "self": 12.789188015999741 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2507884910000371, "count": 1, "self": 0.0011505240000246886, "children": { "RLTrainer._checkpoint": { "total": 0.2496379670000124, "count": 1, "self": 0.2496379670000124 } } } } } } }