{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0823804140090942, "min": 1.0823804140090942, "max": 2.8865561485290527, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10358.380859375, "min": 10358.380859375, "max": 29624.724609375, "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": 2.567681312561035, "min": 0.09589726477861404, "max": 2.574761390686035, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 500.6978759765625, "min": 18.604068756103516, "max": 525.2513427734375, "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": 25.15909090909091, "min": 3.272727272727273, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 144.0, "max": 1389.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.272727272727273, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 144.0, "max": 1389.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.05303531138120246, "min": 0.043000292613321695, "max": 0.05497397439595421, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.10607062276240492, "min": 0.08600058522664339, "max": 0.15276711164316273, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.12043402075548382, "min": 0.05885272711833857, "max": 0.1406230588498361, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.24086804151096763, "min": 0.11770545423667714, "max": 0.4104643968098304, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.432097856000006e-06, "min": 6.432097856000006e-06, "max": 0.00029023200325599993, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.2864195712000013e-05, "min": 1.2864195712000013e-05, "max": 0.0007419960526679999, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10321600000000003, "min": 0.10321600000000003, "max": 0.24511600000000003, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20643200000000006, "min": 0.20643200000000006, "max": 0.6709980000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00011698560000000007, "min": 0.00011698560000000007, "max": 0.004837525599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00023397120000000015, "min": 0.00023397120000000015, "max": 0.012371866800000002, "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": "1694195607", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=SnowballTarget2 --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": "1694196083" }, "total": 475.86589398, "count": 1, "self": 0.43534228899966365, "children": { "run_training.setup": { "total": 0.03870379100021637, "count": 1, "self": 0.03870379100021637 }, "TrainerController.start_learning": { "total": 475.39184790000013, "count": 1, "self": 0.5261172999864812, "children": { "TrainerController._reset_env": { "total": 3.8278629380001803, "count": 1, "self": 3.8278629380001803 }, "TrainerController.advance": { "total": 470.90342204901344, "count": 18202, "self": 0.2622811350365737, "children": { "env_step": { "total": 470.64114091397687, "count": 18202, "self": 348.71422680298383, "children": { "SubprocessEnvManager._take_step": { "total": 121.66394710200075, "count": 18202, "self": 1.755945177010517, "children": { "TorchPolicy.evaluate": { "total": 119.90800192499023, "count": 18202, "self": 119.90800192499023 } } }, "workers": { "total": 0.2629670089922911, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 473.8338290559757, "count": 18202, "is_parallel": true, "self": 236.80496419895894, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018615440001212846, "count": 1, "is_parallel": true, "self": 0.0005025840000598691, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013589600000614155, "count": 10, "is_parallel": true, "self": 0.0013589600000614155 } } }, "UnityEnvironment.step": { "total": 0.03816275599979235, "count": 1, "is_parallel": true, "self": 0.0006009799997173104, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033410600008210167, "count": 1, "is_parallel": true, "self": 0.00033410600008210167 }, "communicator.exchange": { "total": 0.0350276470001063, "count": 1, "is_parallel": true, "self": 0.0350276470001063 }, "steps_from_proto": { "total": 0.0022000229998866416, "count": 1, "is_parallel": true, "self": 0.000523639999983061, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016763829999035806, "count": 10, "is_parallel": true, "self": 0.0016763829999035806 } } } } } } }, "UnityEnvironment.step": { "total": 237.02886485701674, "count": 18201, "is_parallel": true, "self": 10.0921474280849, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2441317659774995, "count": 18201, "is_parallel": true, "self": 5.2441317659774995 }, "communicator.exchange": { "total": 186.9509997249993, "count": 18201, "is_parallel": true, "self": 186.9509997249993 }, "steps_from_proto": { "total": 34.74158593795505, "count": 18201, "is_parallel": true, "self": 6.252948916890773, "children": { "_process_rank_one_or_two_observation": { "total": 28.488637021064278, "count": 182010, "is_parallel": true, "self": 28.488637021064278 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015687999984947965, "count": 1, "self": 0.00015687999984947965, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 466.432363791929, "count": 526672, "is_parallel": true, "self": 11.80509066705963, "children": { "process_trajectory": { "total": 299.5110636478719, "count": 526672, "is_parallel": true, "self": 298.73790789987197, "children": { "RLTrainer._checkpoint": { "total": 0.7731557479999083, "count": 4, "is_parallel": true, "self": 0.7731557479999083 } } }, "_update_policy": { "total": 155.11620947699748, "count": 45, "is_parallel": true, "self": 87.08159226400198, "children": { "TorchPPOOptimizer.update": { "total": 68.0346172129955, "count": 3056, "is_parallel": true, "self": 68.0346172129955 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13428873300017585, "count": 1, "self": 0.0006541750003634661, "children": { "RLTrainer._checkpoint": { "total": 0.1336345579998124, "count": 1, "self": 0.1336345579998124 } } } } } } }