{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7655732035636902, "min": 0.7655732035636902, "max": 2.8725733757019043, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7318.1142578125, "min": 7318.1142578125, "max": 29386.42578125, "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": 12.048530578613281, "min": 0.3474101126194, "max": 12.048530578613281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2349.46337890625, "min": 67.3975601196289, "max": 2407.87451171875, "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": 0.0667594604582893, "min": 0.06165375752244989, "max": 0.07622424663086172, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2670378418331572, "min": 0.24837828063908662, "max": 0.3774015305942728, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20024365446000708, "min": 0.12685778356321595, "max": 0.2820342378143002, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8009746178400283, "min": 0.5074311342528638, "max": 1.326773105590951, "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": 24.25, "min": 3.477272727272727, "max": 24.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1067.0, "min": 153.0, "max": 1293.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.25, "min": 3.477272727272727, "max": 24.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1067.0, "min": 153.0, "max": 1293.0, "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": "1679231918", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679232375" }, "total": 457.62724795200006, "count": 1, "self": 0.48760623099997247, "children": { "run_training.setup": { "total": 0.1889293080000698, "count": 1, "self": 0.1889293080000698 }, "TrainerController.start_learning": { "total": 456.950712413, "count": 1, "self": 0.5306185469944467, "children": { "TrainerController._reset_env": { "total": 8.669087413999932, "count": 1, "self": 8.669087413999932 }, "TrainerController.advance": { "total": 447.62166624200574, "count": 18202, "self": 0.2609101980167452, "children": { "env_step": { "total": 447.360756043989, "count": 18202, "self": 326.26921365599765, "children": { "SubprocessEnvManager._take_step": { "total": 120.83820092599467, "count": 18202, "self": 2.6500952969980744, "children": { "TorchPolicy.evaluate": { "total": 118.1881056289966, "count": 18202, "self": 118.1881056289966 } } }, "workers": { "total": 0.2533414619966834, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 455.60697510600903, "count": 18202, "is_parallel": true, "self": 216.6428573210061, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007090177000009135, "count": 1, "is_parallel": true, "self": 0.0048095449998299955, "children": { "_process_rank_one_or_two_observation": { "total": 0.002280632000179139, "count": 10, "is_parallel": true, "self": 0.002280632000179139 } } }, "UnityEnvironment.step": { "total": 0.03420779400005358, "count": 1, "is_parallel": true, "self": 0.000529696000057811, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028933999999480875, "count": 1, "is_parallel": true, "self": 0.00028933999999480875 }, "communicator.exchange": { "total": 0.03145083499998691, "count": 1, "is_parallel": true, "self": 0.03145083499998691 }, "steps_from_proto": { "total": 0.0019379230000140524, "count": 1, "is_parallel": true, "self": 0.00041536599985647626, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015225570001575761, "count": 10, "is_parallel": true, "self": 0.0015225570001575761 } } } } } } }, "UnityEnvironment.step": { "total": 238.96411778500294, "count": 18201, "is_parallel": true, "self": 9.343171111000174, "children": { "UnityEnvironment._generate_step_input": { "total": 5.058271106006146, "count": 18201, "is_parallel": true, "self": 5.058271106006146 }, "communicator.exchange": { "total": 194.4011254880005, "count": 18201, "is_parallel": true, "self": 194.4011254880005 }, "steps_from_proto": { "total": 30.16155007999612, "count": 18201, "is_parallel": true, "self": 5.8764773960245975, "children": { "_process_rank_one_or_two_observation": { "total": 24.28507268397152, "count": 182010, "is_parallel": true, "self": 24.28507268397152 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010242799999105046, "count": 1, "self": 0.00010242799999105046, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 444.47266094198187, "count": 393678, "is_parallel": true, "self": 9.26500269500923, "children": { "process_trajectory": { "total": 246.5420167159723, "count": 393678, "is_parallel": true, "self": 245.37045974197235, "children": { "RLTrainer._checkpoint": { "total": 1.171556973999941, "count": 4, "is_parallel": true, "self": 1.171556973999941 } } }, "_update_policy": { "total": 188.66564153100035, "count": 90, "is_parallel": true, "self": 71.06868328999929, "children": { "TorchPPOOptimizer.update": { "total": 117.59695824100106, "count": 4587, "is_parallel": true, "self": 117.59695824100106 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12923778199990466, "count": 1, "self": 0.0008965989999296653, "children": { "RLTrainer._checkpoint": { "total": 0.128341182999975, "count": 1, "self": 0.128341182999975 } } } } } } }