{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6798049211502075, "min": 0.6798049211502075, "max": 2.8201305866241455, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6460.8662109375, "min": 6460.8662109375, "max": 28787.892578125, "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": 12.768742561340332, "min": 0.2765141427516937, "max": 12.768742561340332, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2489.90478515625, "min": 53.64374542236328, "max": 2580.314453125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06550666011810559, "min": 0.06543751237092212, "max": 0.0758356780992757, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26202664047242236, "min": 0.26202664047242236, "max": 0.3684533002983788, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20645594516513394, "min": 0.12125371630399434, "max": 0.2750681424257802, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8258237806605357, "min": 0.48501486521597736, "max": 1.375340712128901, "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": 25.318181818181817, "min": 3.159090909090909, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1114.0, "min": 139.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.318181818181817, "min": 3.159090909090909, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1114.0, "min": 139.0, "max": 1390.0, "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": "1748884120", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748884554" }, "total": 433.94870199599995, "count": 1, "self": 0.6509147970000413, "children": { "run_training.setup": { "total": 0.022723673999962557, "count": 1, "self": 0.022723673999962557 }, "TrainerController.start_learning": { "total": 433.27506352499995, "count": 1, "self": 0.3868944579746767, "children": { "TrainerController._reset_env": { "total": 3.467201335000027, "count": 1, "self": 3.467201335000027 }, "TrainerController.advance": { "total": 429.28682352502506, "count": 18192, "self": 0.40003925202108803, "children": { "env_step": { "total": 307.7881137920008, "count": 18192, "self": 235.12924584601615, "children": { "SubprocessEnvManager._take_step": { "total": 72.44319310699939, "count": 18192, "self": 1.3729484370001046, "children": { "TorchPolicy.evaluate": { "total": 71.07024466999928, "count": 18192, "self": 71.07024466999928 } } }, "workers": { "total": 0.21567483898525097, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 431.7327463379863, "count": 18192, "is_parallel": true, "self": 225.83495888598554, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0061283000000003085, "count": 1, "is_parallel": true, "self": 0.004295780999882481, "children": { "_process_rank_one_or_two_observation": { "total": 0.001832519000117827, "count": 10, "is_parallel": true, "self": 0.001832519000117827 } } }, "UnityEnvironment.step": { "total": 0.03825939400007883, "count": 1, "is_parallel": true, "self": 0.0005763600001955638, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041246399996452965, "count": 1, "is_parallel": true, "self": 0.00041246399996452965 }, "communicator.exchange": { "total": 0.035341732999995656, "count": 1, "is_parallel": true, "self": 0.035341732999995656 }, "steps_from_proto": { "total": 0.0019288369999230781, "count": 1, "is_parallel": true, "self": 0.00038230699988162087, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015465300000414572, "count": 10, "is_parallel": true, "self": 0.0015465300000414572 } } } } } } }, "UnityEnvironment.step": { "total": 205.89778745200078, "count": 18191, "is_parallel": true, "self": 9.972489712966762, "children": { "UnityEnvironment._generate_step_input": { "total": 5.614227041988215, "count": 18191, "is_parallel": true, "self": 5.614227041988215 }, "communicator.exchange": { "total": 157.77374893401975, "count": 18191, "is_parallel": true, "self": 157.77374893401975 }, "steps_from_proto": { "total": 32.53732176302606, "count": 18191, "is_parallel": true, "self": 5.914539362065398, "children": { "_process_rank_one_or_two_observation": { "total": 26.62278240096066, "count": 181910, "is_parallel": true, "self": 26.62278240096066 } } } } } } } } } } }, "trainer_advance": { "total": 121.09867048100318, "count": 18192, "self": 0.4688672329925794, "children": { "process_trajectory": { "total": 27.715222680010584, "count": 18192, "self": 27.251183399010188, "children": { "RLTrainer._checkpoint": { "total": 0.46403928100039593, "count": 4, "self": 0.46403928100039593 } } }, "_update_policy": { "total": 92.91458056800002, "count": 90, "self": 37.921738379993485, "children": { "TorchPPOOptimizer.update": { "total": 54.992842188006534, "count": 4587, "self": 54.992842188006534 } } } } } } }, "trainer_threads": { "total": 1.6550002328585833e-06, "count": 1, "self": 1.6550002328585833e-06 }, "TrainerController._save_models": { "total": 0.1341425519999575, "count": 1, "self": 0.001228884999818547, "children": { "RLTrainer._checkpoint": { "total": 0.13291366700013896, "count": 1, "self": 0.13291366700013896 } } } } } } }