{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9037644863128662, "min": 0.9037644863128662, "max": 2.8764915466308594, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8678.8505859375, "min": 8678.8505859375, "max": 29521.431640625, "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": 12.885485649108887, "min": 0.3949391543865204, "max": 12.885485649108887, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2512.669677734375, "min": 76.61819458007812, "max": 2627.9228515625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06491138747090493, "min": 0.06404384929873963, "max": 0.07714593876830181, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2596455498836197, "min": 0.25874071807340765, "max": 0.385729693841509, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17815244300108332, "min": 0.12212129700563702, "max": 0.26987962052226067, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7126097720043333, "min": 0.4884851880225481, "max": 1.3485119506424548, "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": 25.477272727272727, "min": 3.4545454545454546, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 152.0, "max": 1379.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.4545454545454546, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 152.0, "max": 1379.0, "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": "1701692467", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701692964" }, "total": 497.50024344400003, "count": 1, "self": 0.7999101039999914, "children": { "run_training.setup": { "total": 0.06570449700006975, "count": 1, "self": 0.06570449700006975 }, "TrainerController.start_learning": { "total": 496.634628843, "count": 1, "self": 0.6434393009986934, "children": { "TrainerController._reset_env": { "total": 3.4396155559999215, "count": 1, "self": 3.4396155559999215 }, "TrainerController.advance": { "total": 492.38186711000117, "count": 18209, "self": 0.30814155398957155, "children": { "env_step": { "total": 492.0737255560116, "count": 18209, "self": 333.7106801990077, "children": { "SubprocessEnvManager._take_step": { "total": 158.0406304490043, "count": 18209, "self": 1.5678745040140711, "children": { "TorchPolicy.evaluate": { "total": 156.47275594499024, "count": 18209, "self": 156.47275594499024 } } }, "workers": { "total": 0.32241490799958683, "count": 18209, "self": 0.0, "children": { "worker_root": { "total": 495.21515393900984, "count": 18209, "is_parallel": true, "self": 242.74301020500343, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004934515999934774, "count": 1, "is_parallel": true, "self": 0.003483502000108274, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014510139998265004, "count": 10, "is_parallel": true, "self": 0.0014510139998265004 } } }, "UnityEnvironment.step": { "total": 0.09613084900001923, "count": 1, "is_parallel": true, "self": 0.0006493849999742451, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000435938000009628, "count": 1, "is_parallel": true, "self": 0.000435938000009628 }, "communicator.exchange": { "total": 0.09286819900000864, "count": 1, "is_parallel": true, "self": 0.09286819900000864 }, "steps_from_proto": { "total": 0.0021773270000267075, "count": 1, "is_parallel": true, "self": 0.0004366590001154691, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017406679999112384, "count": 10, "is_parallel": true, "self": 0.0017406679999112384 } } } } } } }, "UnityEnvironment.step": { "total": 252.4721437340064, "count": 18208, "is_parallel": true, "self": 10.873109749996274, "children": { "UnityEnvironment._generate_step_input": { "total": 5.605729570000221, "count": 18208, "is_parallel": true, "self": 5.605729570000221 }, "communicator.exchange": { "total": 199.63012752999612, "count": 18208, "is_parallel": true, "self": 199.63012752999612 }, "steps_from_proto": { "total": 36.3631768840138, "count": 18208, "is_parallel": true, "self": 6.999627789998954, "children": { "_process_rank_one_or_two_observation": { "total": 29.363549094014843, "count": 182080, "is_parallel": true, "self": 29.363549094014843 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001380860001063411, "count": 1, "self": 0.0001380860001063411, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 488.12124106101135, "count": 522448, "is_parallel": true, "self": 11.577969568998583, "children": { "process_trajectory": { "total": 276.84171136701366, "count": 522448, "is_parallel": true, "self": 276.0438904710138, "children": { "RLTrainer._checkpoint": { "total": 0.7978208959998483, "count": 4, "is_parallel": true, "self": 0.7978208959998483 } } }, "_update_policy": { "total": 199.7015601249991, "count": 90, "is_parallel": true, "self": 60.40804029600611, "children": { "TorchPPOOptimizer.update": { "total": 139.293519828993, "count": 4587, "is_parallel": true, "self": 139.293519828993 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16956879000008485, "count": 1, "self": 0.002217746000042098, "children": { "RLTrainer._checkpoint": { "total": 0.16735104400004275, "count": 1, "self": 0.16735104400004275 } } } } } } }