{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.041369915008545, "min": 1.0346976518630981, "max": 2.875018835067749, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9931.544921875, "min": 9931.544921875, "max": 28578.875, "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": 11.814372062683105, "min": 0.2857319712638855, "max": 11.814372062683105, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2303.802490234375, "min": 42.85979461669922, "max": 2401.56396484375, "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": 6567.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.065571860594312, "min": 0.06273355996227645, "max": 0.07468478080226025, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.262287442377248, "min": 0.22405434240678074, "max": 0.3724314922925687, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20481071007602356, "min": 0.11864467222377462, "max": 0.29244302863291666, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8192428403040942, "min": 0.35593401667132385, "max": 1.4042382056222242, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000290232003256, "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": 0.19674400000000003, "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": 0.0048375256, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.227272727272727, "min": 3.212121212121212, "max": 23.618181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1022.0, "min": 106.0, "max": 1299.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.227272727272727, "min": 3.212121212121212, "max": 23.618181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1022.0, "min": 106.0, "max": 1299.0, "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": "1682135410", "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 --resume --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": "1682135922" }, "total": 512.04022202, "count": 1, "self": 0.4237399239998467, "children": { "run_training.setup": { "total": 0.10602704200005064, "count": 1, "self": 0.10602704200005064 }, "TrainerController.start_learning": { "total": 511.5104550540001, "count": 1, "self": 0.6490002220032238, "children": { "TrainerController._reset_env": { "total": 4.8784342720000495, "count": 1, "self": 4.8784342720000495 }, "TrainerController.advance": { "total": 505.83338551999657, "count": 18000, "self": 0.3194009660038546, "children": { "env_step": { "total": 505.5139845539927, "count": 18000, "self": 369.4979241889912, "children": { "SubprocessEnvManager._take_step": { "total": 135.68506729999706, "count": 18000, "self": 1.9702587929929223, "children": { "TorchPolicy.evaluate": { "total": 133.71480850700414, "count": 18000, "self": 133.71480850700414 } } }, "workers": { "total": 0.33099306500446346, "count": 18000, "self": 0.0, "children": { "worker_root": { "total": 509.6941054699919, "count": 18000, "is_parallel": true, "self": 233.222040239992, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002802558000098543, "count": 1, "is_parallel": true, "self": 0.0007304839998596435, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020720740002388993, "count": 10, "is_parallel": true, "self": 0.0020720740002388993 } } }, "UnityEnvironment.step": { "total": 0.10695964299998195, "count": 1, "is_parallel": true, "self": 0.0006320960000039122, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046700799998689035, "count": 1, "is_parallel": true, "self": 0.00046700799998689035 }, "communicator.exchange": { "total": 0.10370971099996495, "count": 1, "is_parallel": true, "self": 0.10370971099996495 }, "steps_from_proto": { "total": 0.002150828000026195, "count": 1, "is_parallel": true, "self": 0.0005181190000485003, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016327089999776945, "count": 10, "is_parallel": true, "self": 0.0016327089999776945 } } } } } } }, "UnityEnvironment.step": { "total": 276.4720652299999, "count": 17999, "is_parallel": true, "self": 10.83718196600887, "children": { "UnityEnvironment._generate_step_input": { "total": 6.174316922004095, "count": 17999, "is_parallel": true, "self": 6.174316922004095 }, "communicator.exchange": { "total": 222.4295646639987, "count": 17999, "is_parallel": true, "self": 222.4295646639987 }, "steps_from_proto": { "total": 37.03100167798823, "count": 17999, "is_parallel": true, "self": 7.621838358995433, "children": { "_process_rank_one_or_two_observation": { "total": 29.409163318992796, "count": 179990, "is_parallel": true, "self": 29.409163318992796 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012425900013113278, "count": 1, "self": 0.00012425900013113278, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 501.526204148974, "count": 460023, "is_parallel": true, "self": 12.105777392945015, "children": { "process_trajectory": { "total": 279.58042326002885, "count": 460023, "is_parallel": true, "self": 278.786186531029, "children": { "RLTrainer._checkpoint": { "total": 0.7942367289998629, "count": 4, "is_parallel": true, "self": 0.7942367289998629 } } }, "_update_policy": { "total": 209.84000349600012, "count": 89, "is_parallel": true, "self": 76.4112699529934, "children": { "TorchPPOOptimizer.update": { "total": 133.42873354300673, "count": 4536, "is_parallel": true, "self": 133.42873354300673 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14951078100011728, "count": 1, "self": 0.0010954260001199145, "children": { "RLTrainer._checkpoint": { "total": 0.14841535499999736, "count": 1, "self": 0.14841535499999736 } } } } } } }