{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6420794725418091, "min": 0.6361227035522461, "max": 2.8625614643096924, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6102.3232421875, "min": 6102.3232421875, "max": 29221.02734375, "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": 13.06202220916748, "min": 0.36747294664382935, "max": 13.06202220916748, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2547.09423828125, "min": 71.28974914550781, "max": 2640.01025390625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06840230639243279, "min": 0.061013617379449346, "max": 0.07586432524593358, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27360922556973116, "min": 0.24632764607325525, "max": 0.3728978453505346, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21091302878716411, "min": 0.12741706437002137, "max": 0.2779288382506838, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8436521151486565, "min": 0.5096682574800855, "max": 1.373724123718692, "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": 25.886363636363637, "min": 3.4318181818181817, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 151.0, "max": 1410.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 3.4318181818181817, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 151.0, "max": 1410.0, "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": "1778521466", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/home/oleksii/PycharmProjects/flock_systems/snowball/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1778521779" }, "total": 313.38282723600423, "count": 1, "self": 0.26955933700082824, "children": { "run_training.setup": { "total": 0.01643479899939848, "count": 1, "self": 0.01643479899939848 }, "TrainerController.start_learning": { "total": 313.096833100004, "count": 1, "self": 0.3404079314423143, "children": { "TrainerController._reset_env": { "total": 1.910869407998689, "count": 1, "self": 1.910869407998689 }, "TrainerController.advance": { "total": 310.7795633975693, "count": 18192, "self": 0.3533924282019143, "children": { "env_step": { "total": 212.84258436134405, "count": 18192, "self": 151.3749125263057, "children": { "SubprocessEnvManager._take_step": { "total": 61.24833318913443, "count": 18192, "self": 1.1408163912055898, "children": { "TorchPolicy.evaluate": { "total": 60.10751679792884, "count": 18192, "self": 60.10751679792884 } } }, "workers": { "total": 0.2193386459039175, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 312.4633415716671, "count": 18192, "is_parallel": true, "self": 182.9182145591185, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001731894000840839, "count": 1, "is_parallel": true, "self": 0.0004863609865424223, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012455330142984167, "count": 10, "is_parallel": true, "self": 0.0012455330142984167 } } }, "UnityEnvironment.step": { "total": 0.026465475995792076, "count": 1, "is_parallel": true, "self": 0.0003512539915391244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002934750009444542, "count": 1, "is_parallel": true, "self": 0.0002934750009444542 }, "communicator.exchange": { "total": 0.02472687700355891, "count": 1, "is_parallel": true, "self": 0.02472687700355891 }, "steps_from_proto": { "total": 0.001093869999749586, "count": 1, "is_parallel": true, "self": 0.00023471700842492282, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008591529913246632, "count": 10, "is_parallel": true, "self": 0.0008591529913246632 } } } } } } }, "UnityEnvironment.step": { "total": 129.54512701254862, "count": 18191, "is_parallel": true, "self": 5.331997508568747, "children": { "UnityEnvironment._generate_step_input": { "total": 3.4495551276559127, "count": 18191, "is_parallel": true, "self": 3.4495551276559127 }, "communicator.exchange": { "total": 103.56084264751553, "count": 18191, "is_parallel": true, "self": 103.56084264751553 }, "steps_from_proto": { "total": 17.20273172880843, "count": 18191, "is_parallel": true, "self": 3.688950464980735, "children": { "_process_rank_one_or_two_observation": { "total": 13.513781263827696, "count": 181910, "is_parallel": true, "self": 13.513781263827696 } } } } } } } } } } }, "trainer_advance": { "total": 97.58358660802332, "count": 18192, "self": 0.4206014292212785, "children": { "process_trajectory": { "total": 20.910001259777346, "count": 18192, "self": 20.59959193177201, "children": { "RLTrainer._checkpoint": { "total": 0.31040932800533483, "count": 4, "self": 0.31040932800533483 } } }, "_update_policy": { "total": 76.2529839190247, "count": 90, "self": 28.594975057021657, "children": { "TorchPPOOptimizer.update": { "total": 47.658008862003044, "count": 4587, "self": 47.658008862003044 } } } } } } }, "trainer_threads": { "total": 1.1919983080588281e-06, "count": 1, "self": 1.1919983080588281e-06 }, "TrainerController._save_models": { "total": 0.06599117099540308, "count": 1, "self": 0.0005402479946496896, "children": { "RLTrainer._checkpoint": { "total": 0.06545092300075339, "count": 1, "self": 0.06545092300075339 } } } } } } }