{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8235909938812256, "min": 0.8235909938812256, "max": 2.8689613342285156, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7872.7060546875, "min": 7872.7060546875, "max": 29349.474609375, "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": 12.88090705871582, "min": 0.5364781022071838, "max": 12.920222282409668, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2511.77685546875, "min": 104.07675170898438, "max": 2635.725341796875, "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": 0.0682949047410219, "min": 0.06444919249428066, "max": 0.0755566750446508, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2731796189640876, "min": 0.25779676997712264, "max": 0.3722635177848632, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20011386384858806, "min": 0.11510545072629683, "max": 0.28401023611134174, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8004554553943523, "min": 0.4604218029051873, "max": 1.4200511805567086, "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": 25.431818181818183, "min": 3.4318181818181817, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 151.0, "max": 1382.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.4318181818181817, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 151.0, "max": 1382.0, "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": "1704469608", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704470072" }, "total": 464.386375948, "count": 1, "self": 0.4757137000005969, "children": { "run_training.setup": { "total": 0.04851805399994191, "count": 1, "self": 0.04851805399994191 }, "TrainerController.start_learning": { "total": 463.8621441939995, "count": 1, "self": 0.5836285609811966, "children": { "TrainerController._reset_env": { "total": 1.9902926409995416, "count": 1, "self": 1.9902926409995416 }, "TrainerController.advance": { "total": 461.19124147101866, "count": 18200, "self": 0.27535985795657325, "children": { "env_step": { "total": 460.9158816130621, "count": 18200, "self": 306.9469630970607, "children": { "SubprocessEnvManager._take_step": { "total": 153.68316775096537, "count": 18200, "self": 1.4956705969389077, "children": { "TorchPolicy.evaluate": { "total": 152.18749715402646, "count": 18200, "self": 152.18749715402646 } } }, "workers": { "total": 0.2857507650360276, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 462.4355463549891, "count": 18200, "is_parallel": true, "self": 223.56995383302183, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019047410005441634, "count": 1, "is_parallel": true, "self": 0.0005791580024379073, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013255829981062561, "count": 10, "is_parallel": true, "self": 0.0013255829981062561 } } }, "UnityEnvironment.step": { "total": 0.03541301299992483, "count": 1, "is_parallel": true, "self": 0.0005820669994136551, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000372184000298148, "count": 1, "is_parallel": true, "self": 0.000372184000298148 }, "communicator.exchange": { "total": 0.032613944000331685, "count": 1, "is_parallel": true, "self": 0.032613944000331685 }, "steps_from_proto": { "total": 0.001844817999881343, "count": 1, "is_parallel": true, "self": 0.00035095100156468106, "children": { "_process_rank_one_or_two_observation": { "total": 0.001493866998316662, "count": 10, "is_parallel": true, "self": 0.001493866998316662 } } } } } } }, "UnityEnvironment.step": { "total": 238.8655925219673, "count": 18199, "is_parallel": true, "self": 10.915307010009201, "children": { "UnityEnvironment._generate_step_input": { "total": 5.556330894944949, "count": 18199, "is_parallel": true, "self": 5.556330894944949 }, "communicator.exchange": { "total": 187.56412206495497, "count": 18199, "is_parallel": true, "self": 187.56412206495497 }, "steps_from_proto": { "total": 34.82983255205818, "count": 18199, "is_parallel": true, "self": 6.7822811919804735, "children": { "_process_rank_one_or_two_observation": { "total": 28.047551360077705, "count": 181990, "is_parallel": true, "self": 28.047551360077705 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015143600012379466, "count": 1, "self": 0.00015143600012379466, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 455.31515593260156, "count": 702120, "is_parallel": true, "self": 14.478381639578402, "children": { "process_trajectory": { "total": 251.45813367902065, "count": 702120, "is_parallel": true, "self": 250.85530772202037, "children": { "RLTrainer._checkpoint": { "total": 0.6028259570002774, "count": 4, "is_parallel": true, "self": 0.6028259570002774 } } }, "_update_policy": { "total": 189.3786406140025, "count": 90, "is_parallel": true, "self": 60.38867274094537, "children": { "TorchPPOOptimizer.update": { "total": 128.98996787305714, "count": 4587, "is_parallel": true, "self": 128.98996787305714 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09683008499996504, "count": 1, "self": 0.0009514329994999571, "children": { "RLTrainer._checkpoint": { "total": 0.09587865200046508, "count": 1, "self": 0.09587865200046508 } } } } } } }