{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.895268440246582, "min": 0.895268440246582, "max": 2.8749992847442627, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8567.71875, "min": 8567.71875, "max": 29506.1171875, "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": 12.673504829406738, "min": 0.2214941829442978, "max": 12.673504829406738, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2471.33349609375, "min": 42.969871520996094, "max": 2577.640625, "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": 0.06946045462174488, "min": 0.06150481711494434, "max": 0.07539342011814905, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27784181848697953, "min": 0.24601926845977737, "max": 0.364111369241037, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2134738554995434, "min": 0.11509859103335104, "max": 0.2775243919561891, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8538954219981736, "min": 0.4603943641334042, "max": 1.364151045680046, "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": 24.477272727272727, "min": 3.0, "max": 25.29090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1077.0, "min": 132.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.477272727272727, "min": 3.0, "max": 25.29090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1077.0, "min": 132.0, "max": 1391.0, "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": "1720825642", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720826227" }, "total": 585.203095495, "count": 1, "self": 0.538737595999919, "children": { "run_training.setup": { "total": 0.06834357900004306, "count": 1, "self": 0.06834357900004306 }, "TrainerController.start_learning": { "total": 584.59601432, "count": 1, "self": 0.8410461759876853, "children": { "TrainerController._reset_env": { "total": 3.062959048000039, "count": 1, "self": 3.062959048000039 }, "TrainerController.advance": { "total": 580.5792970490123, "count": 18204, "self": 0.4214303680099647, "children": { "env_step": { "total": 580.1578666810024, "count": 18204, "self": 446.4205686189964, "children": { "SubprocessEnvManager._take_step": { "total": 133.33588738000208, "count": 18204, "self": 2.4106887550102556, "children": { "TorchPolicy.evaluate": { "total": 130.92519862499182, "count": 18204, "self": 130.92519862499182 } } }, "workers": { "total": 0.40141068200387053, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 582.6302694179972, "count": 18204, "is_parallel": true, "self": 273.1198734360078, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005323061000012785, "count": 1, "is_parallel": true, "self": 0.0032969209999578197, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020261400000549656, "count": 10, "is_parallel": true, "self": 0.0020261400000549656 } } }, "UnityEnvironment.step": { "total": 0.044033296999998583, "count": 1, "is_parallel": true, "self": 0.0009700640000005478, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000490597999998954, "count": 1, "is_parallel": true, "self": 0.000490597999998954 }, "communicator.exchange": { "total": 0.04008636999998316, "count": 1, "is_parallel": true, "self": 0.04008636999998316 }, "steps_from_proto": { "total": 0.002486265000015919, "count": 1, "is_parallel": true, "self": 0.00047093000006270813, "children": { "_process_rank_one_or_two_observation": { "total": 0.002015334999953211, "count": 10, "is_parallel": true, "self": 0.002015334999953211 } } } } } } }, "UnityEnvironment.step": { "total": 309.51039598198935, "count": 18203, "is_parallel": true, "self": 14.909938391996718, "children": { "UnityEnvironment._generate_step_input": { "total": 7.634012563005342, "count": 18203, "is_parallel": true, "self": 7.634012563005342 }, "communicator.exchange": { "total": 242.46121387699577, "count": 18203, "is_parallel": true, "self": 242.46121387699577 }, "steps_from_proto": { "total": 44.505231149991516, "count": 18203, "is_parallel": true, "self": 8.897566137014223, "children": { "_process_rank_one_or_two_observation": { "total": 35.60766501297729, "count": 182030, "is_parallel": true, "self": 35.60766501297729 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021757399997568427, "count": 1, "self": 0.00021757399997568427, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 573.8325701290195, "count": 769794, "is_parallel": true, "self": 17.338720169111753, "children": { "process_trajectory": { "total": 312.34877172890856, "count": 769794, "is_parallel": true, "self": 311.6245870869086, "children": { "RLTrainer._checkpoint": { "total": 0.7241846419999547, "count": 4, "is_parallel": true, "self": 0.7241846419999547 } } }, "_update_policy": { "total": 244.14507823099916, "count": 90, "is_parallel": true, "self": 69.81046758699699, "children": { "TorchPPOOptimizer.update": { "total": 174.33461064400217, "count": 4587, "is_parallel": true, "self": 174.33461064400217 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11249447299996973, "count": 1, "self": 0.001418942999976025, "children": { "RLTrainer._checkpoint": { "total": 0.1110755299999937, "count": 1, "self": 0.1110755299999937 } } } } } } }