{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0865551233291626, "min": 1.0865551233291626, "max": 2.8643720149993896, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10398.33203125, "min": 10398.33203125, "max": 29365.541015625, "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": 12.851905822753906, "min": 0.47187501192092896, "max": 12.851905822753906, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2506.12158203125, "min": 91.54375457763672, "max": 2593.541748046875, "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": 0.06455208984998001, "min": 0.06296711615731884, "max": 0.07740213806718042, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25820835939992004, "min": 0.25757554458259085, "max": 0.3618928202731516, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21049675243157967, "min": 0.12819662993869688, "max": 0.2886557080582076, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8419870097263187, "min": 0.5127865197547875, "max": 1.4432785402910382, "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": 25.568181818181817, "min": 3.477272727272727, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 153.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 3.477272727272727, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 153.0, "max": 1378.0, "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": "1687568335", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687568788" }, "total": 453.14598919199994, "count": 1, "self": 0.3868486089998555, "children": { "run_training.setup": { "total": 0.03900604400001839, "count": 1, "self": 0.03900604400001839 }, "TrainerController.start_learning": { "total": 452.72013453900007, "count": 1, "self": 0.5590352930066729, "children": { "TrainerController._reset_env": { "total": 4.049816050000004, "count": 1, "self": 4.049816050000004 }, "TrainerController.advance": { "total": 447.9763460439934, "count": 18205, "self": 0.24483193899754951, "children": { "env_step": { "total": 447.7315141049958, "count": 18205, "self": 325.57897442200033, "children": { "SubprocessEnvManager._take_step": { "total": 121.89742095499878, "count": 18205, "self": 1.6609821860004672, "children": { "TorchPolicy.evaluate": { "total": 120.23643876899831, "count": 18205, "self": 120.23643876899831 } } }, "workers": { "total": 0.25511872799671664, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 451.2204801349967, "count": 18205, "is_parallel": true, "self": 212.23919909899269, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005640315999983159, "count": 1, "is_parallel": true, "self": 0.004138223000040853, "children": { "_process_rank_one_or_two_observation": { "total": 0.001502092999942306, "count": 10, "is_parallel": true, "self": 0.001502092999942306 } } }, "UnityEnvironment.step": { "total": 0.034378076999985296, "count": 1, "is_parallel": true, "self": 0.000564151000048696, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003899029999843151, "count": 1, "is_parallel": true, "self": 0.0003899029999843151 }, "communicator.exchange": { "total": 0.03140231899999435, "count": 1, "is_parallel": true, "self": 0.03140231899999435 }, "steps_from_proto": { "total": 0.0020217039999579356, "count": 1, "is_parallel": true, "self": 0.00034902400000191847, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016726799999560171, "count": 10, "is_parallel": true, "self": 0.0016726799999560171 } } } } } } }, "UnityEnvironment.step": { "total": 238.98128103600402, "count": 18204, "is_parallel": true, "self": 9.951518611025563, "children": { "UnityEnvironment._generate_step_input": { "total": 5.010116514993285, "count": 18204, "is_parallel": true, "self": 5.010116514993285 }, "communicator.exchange": { "total": 190.77522246299958, "count": 18204, "is_parallel": true, "self": 190.77522246299958 }, "steps_from_proto": { "total": 33.24442344698559, "count": 18204, "is_parallel": true, "self": 6.054082681996988, "children": { "_process_rank_one_or_two_observation": { "total": 27.190340764988605, "count": 182040, "is_parallel": true, "self": 27.190340764988605 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013355600003706058, "count": 1, "self": 0.00013355600003706058, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 444.56358680404395, "count": 420534, "is_parallel": true, "self": 9.388259424076466, "children": { "process_trajectory": { "total": 243.89127730396774, "count": 420534, "is_parallel": true, "self": 243.07553540096785, "children": { "RLTrainer._checkpoint": { "total": 0.8157419029998891, "count": 4, "is_parallel": true, "self": 0.8157419029998891 } } }, "_update_policy": { "total": 191.28405007599974, "count": 90, "is_parallel": true, "self": 73.30903239999594, "children": { "TorchPPOOptimizer.update": { "total": 117.9750176760038, "count": 4587, "is_parallel": true, "self": 117.9750176760038 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13480359599998337, "count": 1, "self": 0.0008489089999557109, "children": { "RLTrainer._checkpoint": { "total": 0.13395468700002766, "count": 1, "self": 0.13395468700002766 } } } } } } }