{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0199246406555176, "min": 1.0199246406555176, "max": 2.8538265228271484, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9738.240234375, "min": 9738.240234375, "max": 29194.64453125, "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": 12.676046371459961, "min": 0.14666564762592316, "max": 12.676046371459961, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2471.8291015625, "min": 28.453136444091797, "max": 2577.89794921875, "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": 0.07431003886677881, "min": 0.06301956523812431, "max": 0.07431003886677881, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29724015546711524, "min": 0.2571182431477378, "max": 0.36866475900009676, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22434938888923794, "min": 0.11079428415042439, "max": 0.28154752610945233, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8973975555569518, "min": 0.44317713660169755, "max": 1.4077376305472615, "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": 25.0, "min": 3.272727272727273, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 144.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.272727272727273, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 144.0, "max": 1381.0, "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": "1686555606", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1686556090" }, "total": 483.81287726899996, "count": 1, "self": 0.4386677669999699, "children": { "run_training.setup": { "total": 0.04113501400001951, "count": 1, "self": 0.04113501400001951 }, "TrainerController.start_learning": { "total": 483.33307448799997, "count": 1, "self": 0.5937868630068124, "children": { "TrainerController._reset_env": { "total": 4.81646604499997, "count": 1, "self": 4.81646604499997 }, "TrainerController.advance": { "total": 477.7825102999931, "count": 18202, "self": 0.29438425599346374, "children": { "env_step": { "total": 477.4881260439996, "count": 18202, "self": 347.48027918000446, "children": { "SubprocessEnvManager._take_step": { "total": 129.69838081100067, "count": 18202, "self": 1.8592176650066676, "children": { "TorchPolicy.evaluate": { "total": 127.83916314599401, "count": 18202, "self": 127.83916314599401 } } }, "workers": { "total": 0.3094660529944804, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 481.6222364020025, "count": 18202, "is_parallel": true, "self": 224.50564655100698, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005176987000027111, "count": 1, "is_parallel": true, "self": 0.003490162999923996, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016868240001031154, "count": 10, "is_parallel": true, "self": 0.0016868240001031154 } } }, "UnityEnvironment.step": { "total": 0.09202599800005373, "count": 1, "is_parallel": true, "self": 0.0006330470000648347, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003790240000398626, "count": 1, "is_parallel": true, "self": 0.0003790240000398626 }, "communicator.exchange": { "total": 0.08880063599997357, "count": 1, "is_parallel": true, "self": 0.08880063599997357 }, "steps_from_proto": { "total": 0.00221329099997547, "count": 1, "is_parallel": true, "self": 0.0003932209998538383, "children": { "_process_rank_one_or_two_observation": { "total": 0.001820070000121632, "count": 10, "is_parallel": true, "self": 0.001820070000121632 } } } } } } }, "UnityEnvironment.step": { "total": 257.1165898509955, "count": 18201, "is_parallel": true, "self": 10.663191966998284, "children": { "UnityEnvironment._generate_step_input": { "total": 5.412404158001777, "count": 18201, "is_parallel": true, "self": 5.412404158001777 }, "communicator.exchange": { "total": 205.35848143399153, "count": 18201, "is_parallel": true, "self": 205.35848143399153 }, "steps_from_proto": { "total": 35.682512292003935, "count": 18201, "is_parallel": true, "self": 6.611146507061562, "children": { "_process_rank_one_or_two_observation": { "total": 29.071365784942373, "count": 182010, "is_parallel": true, "self": 29.071365784942373 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016681300007803657, "count": 1, "self": 0.00016681300007803657, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 474.19935985897314, "count": 468533, "is_parallel": true, "self": 9.869260101922237, "children": { "process_trajectory": { "total": 260.993350323051, "count": 468533, "is_parallel": true, "self": 260.16897806805105, "children": { "RLTrainer._checkpoint": { "total": 0.8243722549999575, "count": 4, "is_parallel": true, "self": 0.8243722549999575 } } }, "_update_policy": { "total": 203.3367494339999, "count": 90, "is_parallel": true, "self": 76.01625816000444, "children": { "TorchPPOOptimizer.update": { "total": 127.32049127399546, "count": 4587, "is_parallel": true, "self": 127.32049127399546 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14014446700002736, "count": 1, "self": 0.0008987769999748707, "children": { "RLTrainer._checkpoint": { "total": 0.1392456900000525, "count": 1, "self": 0.1392456900000525 } } } } } } }