{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7354112267494202, "min": 0.7354112267494202, "max": 2.8585357666015625, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6989.34814453125, "min": 6989.34814453125, "max": 29179.93359375, "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": 12.762919425964355, "min": 0.2877811789512634, "max": 12.762919425964355, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2488.769287109375, "min": 55.82954788208008, "max": 2603.55078125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0733314545365169, "min": 0.05772037789421459, "max": 0.07581398470931305, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2933258181460676, "min": 0.23088151157685835, "max": 0.37906992354656527, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18946460985085542, "min": 0.11296631571581113, "max": 0.2567696473177742, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7578584394034217, "min": 0.4518652628632445, "max": 1.2838482365888708, "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.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": 25.59090909090909, "min": 3.6818181818181817, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 162.0, "max": 1363.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.6818181818181817, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 162.0, "max": 1363.0, "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": "1739932301", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739932748" }, "total": 446.557492154, "count": 1, "self": 0.4384176870000829, "children": { "run_training.setup": { "total": 0.025021118000040588, "count": 1, "self": 0.025021118000040588 }, "TrainerController.start_learning": { "total": 446.09405334899986, "count": 1, "self": 0.3737622850015896, "children": { "TrainerController._reset_env": { "total": 2.8883850720000055, "count": 1, "self": 2.8883850720000055 }, "TrainerController.advance": { "total": 442.73588319599855, "count": 18192, "self": 0.38438380299987784, "children": { "env_step": { "total": 315.88389358799895, "count": 18192, "self": 239.39123399900393, "children": { "SubprocessEnvManager._take_step": { "total": 76.26437599299675, "count": 18192, "self": 1.3468658739843704, "children": { "TorchPolicy.evaluate": { "total": 74.91751011901238, "count": 18192, "self": 74.91751011901238 } } }, "workers": { "total": 0.22828359599827763, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 444.46885376899286, "count": 18192, "is_parallel": true, "self": 234.75574757600668, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006391162999989319, "count": 1, "is_parallel": true, "self": 0.004111192000095798, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022799709998935214, "count": 10, "is_parallel": true, "self": 0.0022799709998935214 } } }, "UnityEnvironment.step": { "total": 0.03959063799993601, "count": 1, "is_parallel": true, "self": 0.0006393080000179907, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004349949999777891, "count": 1, "is_parallel": true, "self": 0.0004349949999777891 }, "communicator.exchange": { "total": 0.03642972199997985, "count": 1, "is_parallel": true, "self": 0.03642972199997985 }, "steps_from_proto": { "total": 0.00208661299996038, "count": 1, "is_parallel": true, "self": 0.00043233699989286833, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016542760000675116, "count": 10, "is_parallel": true, "self": 0.0016542760000675116 } } } } } } }, "UnityEnvironment.step": { "total": 209.71310619298617, "count": 18191, "is_parallel": true, "self": 9.932578524984251, "children": { "UnityEnvironment._generate_step_input": { "total": 5.718725994003194, "count": 18191, "is_parallel": true, "self": 5.718725994003194 }, "communicator.exchange": { "total": 160.74543190899306, "count": 18191, "is_parallel": true, "self": 160.74543190899306 }, "steps_from_proto": { "total": 33.316369765005675, "count": 18191, "is_parallel": true, "self": 6.043256501997007, "children": { "_process_rank_one_or_two_observation": { "total": 27.273113263008668, "count": 181910, "is_parallel": true, "self": 27.273113263008668 } } } } } } } } } } }, "trainer_advance": { "total": 126.46760580499972, "count": 18192, "self": 0.46518093598251653, "children": { "process_trajectory": { "total": 28.44065380401696, "count": 18192, "self": 27.80490401001714, "children": { "RLTrainer._checkpoint": { "total": 0.6357497939998211, "count": 4, "self": 0.6357497939998211 } } }, "_update_policy": { "total": 97.56177106500024, "count": 90, "self": 39.203680599996915, "children": { "TorchPPOOptimizer.update": { "total": 58.35809046500333, "count": 4587, "self": 58.35809046500333 } } } } } } }, "trainer_threads": { "total": 1.0199998996540671e-06, "count": 1, "self": 1.0199998996540671e-06 }, "TrainerController._save_models": { "total": 0.09602177599981587, "count": 1, "self": 0.0009257239996713906, "children": { "RLTrainer._checkpoint": { "total": 0.09509605200014448, "count": 1, "self": 0.09509605200014448 } } } } } } }