{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8669039011001587, "min": 0.8542680740356445, "max": 2.8539304733276367, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8239.0546875, "min": 8239.0546875, "max": 29132.921875, "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": 13.045256614685059, "min": 0.34381920099258423, "max": 13.045256614685059, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2543.824951171875, "min": 66.700927734375, "max": 2659.551025390625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07671483712778461, "min": 0.06216983036807398, "max": 0.07671483712778461, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30685934851113844, "min": 0.24867932147229593, "max": 0.37510800997576965, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1829497077155347, "min": 0.13138355572443164, "max": 0.32315493396976414, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7317988308621388, "min": 0.5255342228977266, "max": 1.5594984322201972, "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": 25.431818181818183, "min": 3.8636363636363638, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 170.0, "max": 1417.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.8636363636363638, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 170.0, "max": 1417.0, "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": "1746693054", "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": "1746693490" }, "total": 436.034389661, "count": 1, "self": 0.43317475300011665, "children": { "run_training.setup": { "total": 0.033180917999970916, "count": 1, "self": 0.033180917999970916 }, "TrainerController.start_learning": { "total": 435.5680339899999, "count": 1, "self": 0.3564037760061183, "children": { "TrainerController._reset_env": { "total": 3.555696805000025, "count": 1, "self": 3.555696805000025 }, "TrainerController.advance": { "total": 431.57398157799355, "count": 18192, "self": 0.4076620980121106, "children": { "env_step": { "total": 308.11906179800894, "count": 18192, "self": 235.620112046009, "children": { "SubprocessEnvManager._take_step": { "total": 72.27630777398963, "count": 18192, "self": 1.2883949009819844, "children": { "TorchPolicy.evaluate": { "total": 70.98791287300764, "count": 18192, "self": 70.98791287300764 } } }, "workers": { "total": 0.2226419780103015, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 434.14268979900214, "count": 18192, "is_parallel": true, "self": 228.5980197309932, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006460906999905092, "count": 1, "is_parallel": true, "self": 0.004770648999851801, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016902580000532907, "count": 10, "is_parallel": true, "self": 0.0016902580000532907 } } }, "UnityEnvironment.step": { "total": 0.03864218299997901, "count": 1, "is_parallel": true, "self": 0.0005881839999801741, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004322439999668859, "count": 1, "is_parallel": true, "self": 0.0004322439999668859 }, "communicator.exchange": { "total": 0.03567178400010107, "count": 1, "is_parallel": true, "self": 0.03567178400010107 }, "steps_from_proto": { "total": 0.0019499709999308834, "count": 1, "is_parallel": true, "self": 0.000383360999649085, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015666100002817984, "count": 10, "is_parallel": true, "self": 0.0015666100002817984 } } } } } } }, "UnityEnvironment.step": { "total": 205.54467006800894, "count": 18191, "is_parallel": true, "self": 9.848687790005897, "children": { "UnityEnvironment._generate_step_input": { "total": 5.478380924998987, "count": 18191, "is_parallel": true, "self": 5.478380924998987 }, "communicator.exchange": { "total": 158.67712640300056, "count": 18191, "is_parallel": true, "self": 158.67712640300056 }, "steps_from_proto": { "total": 31.5404749500035, "count": 18191, "is_parallel": true, "self": 5.724978705006606, "children": { "_process_rank_one_or_two_observation": { "total": 25.815496244996893, "count": 181910, "is_parallel": true, "self": 25.815496244996893 } } } } } } } } } } }, "trainer_advance": { "total": 123.0472576819725, "count": 18192, "self": 0.45643055796369936, "children": { "process_trajectory": { "total": 28.236974126009045, "count": 18192, "self": 27.769748099009007, "children": { "RLTrainer._checkpoint": { "total": 0.4672260270000379, "count": 4, "self": 0.4672260270000379 } } }, "_update_policy": { "total": 94.35385299799975, "count": 90, "self": 38.69314725399363, "children": { "TorchPPOOptimizer.update": { "total": 55.66070574400612, "count": 4587, "self": 55.66070574400612 } } } } } } }, "trainer_threads": { "total": 8.080000952759292e-07, "count": 1, "self": 8.080000952759292e-07 }, "TrainerController._save_models": { "total": 0.08195102300010149, "count": 1, "self": 0.000861776000192549, "children": { "RLTrainer._checkpoint": { "total": 0.08108924699990894, "count": 1, "self": 0.08108924699990894 } } } } } } }