{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8041669726371765, "min": 0.8041669726371765, "max": 2.855721950531006, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7642.802734375, "min": 7642.802734375, "max": 29151.208984375, "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": 12.905488967895508, "min": 0.42338550090789795, "max": 12.905488967895508, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.5703125, "min": 82.13678741455078, "max": 2631.86767578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06497818002489843, "min": 0.06272427731474084, "max": 0.0767081216799424, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2599127200995937, "min": 0.2584361957766198, "max": 0.383540608399712, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20002296011821896, "min": 0.13244442331065953, "max": 0.27304037543488485, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8000918404728758, "min": 0.5297776932426381, "max": 1.3511978235899231, "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.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.Environment.CumulativeReward.mean": { "value": 25.613636363636363, "min": 3.8863636363636362, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 171.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 3.8863636363636362, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 171.0, "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": "1771658031", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1771658472" }, "total": 440.07823953800016, "count": 1, "self": 0.39792928800011396, "children": { "run_training.setup": { "total": 0.025916262999999162, "count": 1, "self": 0.025916262999999162 }, "TrainerController.start_learning": { "total": 439.65439398700005, "count": 1, "self": 0.3317263479866597, "children": { "TrainerController._reset_env": { "total": 3.267771176999986, "count": 1, "self": 3.267771176999986 }, "TrainerController.advance": { "total": 435.95839585701356, "count": 18192, "self": 0.3520856790155449, "children": { "env_step": { "total": 317.60612013199295, "count": 18192, "self": 248.34749786299858, "children": { "SubprocessEnvManager._take_step": { "total": 69.05203503899384, "count": 18192, "self": 1.2316137489920038, "children": { "TorchPolicy.evaluate": { "total": 67.82042129000183, "count": 18192, "self": 67.82042129000183 } } }, "workers": { "total": 0.2065872300005367, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 437.7732538439917, "count": 18192, "is_parallel": true, "self": 218.9246447599984, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0047883449999517325, "count": 1, "is_parallel": true, "self": 0.0033567119997996997, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014316330001520328, "count": 10, "is_parallel": true, "self": 0.0014316330001520328 } } }, "UnityEnvironment.step": { "total": 0.03513086700002077, "count": 1, "is_parallel": true, "self": 0.0006084290000671899, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003948289999016197, "count": 1, "is_parallel": true, "self": 0.0003948289999016197 }, "communicator.exchange": { "total": 0.03220334900004218, "count": 1, "is_parallel": true, "self": 0.03220334900004218 }, "steps_from_proto": { "total": 0.001924260000009781, "count": 1, "is_parallel": true, "self": 0.0003538460000527266, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015704139999570543, "count": 10, "is_parallel": true, "self": 0.0015704139999570543 } } } } } } }, "UnityEnvironment.step": { "total": 218.84860908399332, "count": 18191, "is_parallel": true, "self": 10.526380033999772, "children": { "UnityEnvironment._generate_step_input": { "total": 5.620161094019068, "count": 18191, "is_parallel": true, "self": 5.620161094019068 }, "communicator.exchange": { "total": 165.77538751298925, "count": 18191, "is_parallel": true, "self": 165.77538751298925 }, "steps_from_proto": { "total": 36.92668044298523, "count": 18191, "is_parallel": true, "self": 6.672700459973157, "children": { "_process_rank_one_or_two_observation": { "total": 30.253979983012073, "count": 181910, "is_parallel": true, "self": 30.253979983012073 } } } } } } } } } } }, "trainer_advance": { "total": 118.00019004600506, "count": 18192, "self": 0.41989795201243396, "children": { "process_trajectory": { "total": 26.15818754199279, "count": 18192, "self": 25.762966515992844, "children": { "RLTrainer._checkpoint": { "total": 0.3952210259999447, "count": 4, "self": 0.3952210259999447 } } }, "_update_policy": { "total": 91.42210455199984, "count": 90, "self": 37.27843014000098, "children": { "TorchPPOOptimizer.update": { "total": 54.14367441199886, "count": 4587, "self": 54.14367441199886 } } } } } } }, "trainer_threads": { "total": 1.314999963142327e-06, "count": 1, "self": 1.314999963142327e-06 }, "TrainerController._save_models": { "total": 0.09649928999988333, "count": 1, "self": 0.0007231019999380806, "children": { "RLTrainer._checkpoint": { "total": 0.09577618799994525, "count": 1, "self": 0.09577618799994525 } } } } } } }