{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6565166711807251, "min": 0.6565166711807251, "max": 2.8403196334838867, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6239.5341796875, "min": 6239.5341796875, "max": 28993.982421875, "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": 12.996484756469727, "min": 0.4993462562561035, "max": 12.996484756469727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2534.314453125, "min": 96.87317657470703, "max": 2621.289306640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06358187932674614, "min": 0.06274275872548221, "max": 0.07336698060070038, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25432751730698455, "min": 0.25097103490192885, "max": 0.36683490300350186, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.188245454145705, "min": 0.1296320199925343, "max": 0.2917931008280492, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.75298181658282, "min": 0.5185280799701372, "max": 1.4086755882291235, "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": 25.636363636363637, "min": 3.9545454545454546, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 174.0, "max": 1412.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 3.9545454545454546, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 174.0, "max": 1412.0, "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": "1740241747", "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": "1740242213" }, "total": 466.411513013, "count": 1, "self": 0.4388753910000105, "children": { "run_training.setup": { "total": 0.023524862000044777, "count": 1, "self": 0.023524862000044777 }, "TrainerController.start_learning": { "total": 465.94911275999993, "count": 1, "self": 0.4652512680122527, "children": { "TrainerController._reset_env": { "total": 2.960148408000009, "count": 1, "self": 2.960148408000009 }, "TrainerController.advance": { "total": 462.43183159798775, "count": 18192, "self": 0.47174821000999145, "children": { "env_step": { "total": 333.72880734698083, "count": 18192, "self": 253.09063531097217, "children": { "SubprocessEnvManager._take_step": { "total": 80.36501849200226, "count": 18192, "self": 1.455856733997507, "children": { "TorchPolicy.evaluate": { "total": 78.90916175800476, "count": 18192, "self": 78.90916175800476 } } }, "workers": { "total": 0.2731535440063908, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 464.1898435439849, "count": 18192, "is_parallel": true, "self": 243.62865277499475, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005368173999954706, "count": 1, "is_parallel": true, "self": 0.003765976000181581, "children": { "_process_rank_one_or_two_observation": { "total": 0.001602197999773125, "count": 10, "is_parallel": true, "self": 0.001602197999773125 } } }, "UnityEnvironment.step": { "total": 0.03766104800001813, "count": 1, "is_parallel": true, "self": 0.0006052249999584092, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004310420000592785, "count": 1, "is_parallel": true, "self": 0.0004310420000592785 }, "communicator.exchange": { "total": 0.034795981999991454, "count": 1, "is_parallel": true, "self": 0.034795981999991454 }, "steps_from_proto": { "total": 0.0018287990000089849, "count": 1, "is_parallel": true, "self": 0.00038027000016427337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014485289998447115, "count": 10, "is_parallel": true, "self": 0.0014485289998447115 } } } } } } }, "UnityEnvironment.step": { "total": 220.56119076899017, "count": 18191, "is_parallel": true, "self": 10.331730785978152, "children": { "UnityEnvironment._generate_step_input": { "total": 5.770617922011979, "count": 18191, "is_parallel": true, "self": 5.770617922011979 }, "communicator.exchange": { "total": 170.77979002599534, "count": 18191, "is_parallel": true, "self": 170.77979002599534 }, "steps_from_proto": { "total": 33.6790520350047, "count": 18191, "is_parallel": true, "self": 6.2800920879767546, "children": { "_process_rank_one_or_two_observation": { "total": 27.398959947027947, "count": 181910, "is_parallel": true, "self": 27.398959947027947 } } } } } } } } } } }, "trainer_advance": { "total": 128.23127604099693, "count": 18192, "self": 0.5971143899919298, "children": { "process_trajectory": { "total": 28.105530774004706, "count": 18192, "self": 27.543297527004825, "children": { "RLTrainer._checkpoint": { "total": 0.562233246999881, "count": 4, "self": 0.562233246999881 } } }, "_update_policy": { "total": 99.5286308770003, "count": 90, "self": 39.72551648900048, "children": { "TorchPPOOptimizer.update": { "total": 59.80311438799981, "count": 4587, "self": 59.80311438799981 } } } } } } }, "trainer_threads": { "total": 8.409999736613827e-07, "count": 1, "self": 8.409999736613827e-07 }, "TrainerController._save_models": { "total": 0.09188064499994653, "count": 1, "self": 0.000938229999746909, "children": { "RLTrainer._checkpoint": { "total": 0.09094241500019962, "count": 1, "self": 0.09094241500019962 } } } } } } }