{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9051306247711182, "min": 0.9051306247711182, "max": 2.8664114475250244, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8652.1435546875, "min": 8652.1435546875, "max": 29417.98046875, "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": 12.215039253234863, "min": 0.48371392488479614, "max": 12.215039253234863, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2381.9326171875, "min": 93.84049987792969, "max": 2458.310546875, "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": 0.06451210274598469, "min": 0.06172351498674948, "max": 0.07939341040373799, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25804841098393877, "min": 0.24689405994699792, "max": 0.3969670520186899, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19134781027541442, "min": 0.11393798118703724, "max": 0.2946517002933166, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7653912411016577, "min": 0.45575192474814896, "max": 1.335608229333279, "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": 24.272727272727273, "min": 3.1363636363636362, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1068.0, "min": 138.0, "max": 1330.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.272727272727273, "min": 3.1363636363636362, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1068.0, "min": 138.0, "max": 1330.0, "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": "1691182663", "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=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": "1691183250" }, "total": 586.5973573739999, "count": 1, "self": 0.49064532599993527, "children": { "run_training.setup": { "total": 0.050486518000070646, "count": 1, "self": 0.050486518000070646 }, "TrainerController.start_learning": { "total": 586.0562255299999, "count": 1, "self": 0.780767562013466, "children": { "TrainerController._reset_env": { "total": 7.183122839000021, "count": 1, "self": 7.183122839000021 }, "TrainerController.advance": { "total": 577.9277657349867, "count": 18200, "self": 0.38053591198104186, "children": { "env_step": { "total": 577.5472298230056, "count": 18200, "self": 425.8018234869895, "children": { "SubprocessEnvManager._take_step": { "total": 151.36701874500807, "count": 18200, "self": 2.318330661993855, "children": { "TorchPolicy.evaluate": { "total": 149.0486880830142, "count": 18200, "self": 149.0486880830142 } } }, "workers": { "total": 0.37838759100804964, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 583.900171719995, "count": 18200, "is_parallel": true, "self": 268.753749247982, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0058096749999094754, "count": 1, "is_parallel": true, "self": 0.0040761569998721825, "children": { "_process_rank_one_or_two_observation": { "total": 0.001733518000037293, "count": 10, "is_parallel": true, "self": 0.001733518000037293 } } }, "UnityEnvironment.step": { "total": 0.056622650000008434, "count": 1, "is_parallel": true, "self": 0.0004946680001012282, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004477109999925233, "count": 1, "is_parallel": true, "self": 0.0004477109999925233 }, "communicator.exchange": { "total": 0.053223345999981575, "count": 1, "is_parallel": true, "self": 0.053223345999981575 }, "steps_from_proto": { "total": 0.0024569249999331078, "count": 1, "is_parallel": true, "self": 0.00045029399973373074, "children": { "_process_rank_one_or_two_observation": { "total": 0.002006631000199377, "count": 10, "is_parallel": true, "self": 0.002006631000199377 } } } } } } }, "UnityEnvironment.step": { "total": 315.146422472013, "count": 18199, "is_parallel": true, "self": 13.14519035802607, "children": { "UnityEnvironment._generate_step_input": { "total": 6.584350200994436, "count": 18199, "is_parallel": true, "self": 6.584350200994436 }, "communicator.exchange": { "total": 250.3000467649972, "count": 18199, "is_parallel": true, "self": 250.3000467649972 }, "steps_from_proto": { "total": 45.11683514799529, "count": 18199, "is_parallel": true, "self": 8.869129612959341, "children": { "_process_rank_one_or_two_observation": { "total": 36.24770553503595, "count": 181990, "is_parallel": true, "self": 36.24770553503595 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.491399994956737e-05, "count": 1, "self": 6.491399994956737e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 573.0928734420482, "count": 553595, "is_parallel": true, "self": 13.575235573080136, "children": { "process_trajectory": { "total": 318.6070524369685, "count": 553595, "is_parallel": true, "self": 317.22577814696854, "children": { "RLTrainer._checkpoint": { "total": 1.3812742899999648, "count": 4, "is_parallel": true, "self": 1.3812742899999648 } } }, "_update_policy": { "total": 240.9105854319996, "count": 90, "is_parallel": true, "self": 96.01743629199188, "children": { "TorchPPOOptimizer.update": { "total": 144.89314914000772, "count": 4587, "is_parallel": true, "self": 144.89314914000772 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1645044799997777, "count": 1, "self": 0.001152857999841217, "children": { "RLTrainer._checkpoint": { "total": 0.16335162199993647, "count": 1, "self": 0.16335162199993647 } } } } } } }