{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9504219889640808, "min": 0.9494279623031616, "max": 2.8311269283294678, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9032.810546875, "min": 9032.810546875, "max": 28900.14453125, "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": 12.204292297363281, "min": 0.33818820118904114, "max": 12.204292297363281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2379.8369140625, "min": 65.60851287841797, "max": 2460.296142578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07062422061198068, "min": 0.06349351931267472, "max": 0.07438325550331273, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2824968824479227, "min": 0.25397407725069887, "max": 0.3574452344556431, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17552158630946102, "min": 0.13593881086939397, "max": 0.3176412168232834, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7020863452378441, "min": 0.5437552434775759, "max": 1.3071585478735903, "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": 24.613636363636363, "min": 3.5681818181818183, "max": 24.613636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1083.0, "min": 157.0, "max": 1312.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.613636363636363, "min": 3.5681818181818183, "max": 24.613636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1083.0, "min": 157.0, "max": 1312.0, "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": "1749529654", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749530110" }, "total": 456.0145887230001, "count": 1, "self": 0.4438102170001912, "children": { "run_training.setup": { "total": 0.031080825000003642, "count": 1, "self": 0.031080825000003642 }, "TrainerController.start_learning": { "total": 455.5396976809999, "count": 1, "self": 0.36732812098739487, "children": { "TrainerController._reset_env": { "total": 3.454732253999964, "count": 1, "self": 3.454732253999964 }, "TrainerController.advance": { "total": 451.6331402190127, "count": 18192, "self": 0.402709586013998, "children": { "env_step": { "total": 324.4676820750011, "count": 18192, "self": 247.38201901197874, "children": { "SubprocessEnvManager._take_step": { "total": 76.86924223800952, "count": 18192, "self": 1.3771210700049323, "children": { "TorchPolicy.evaluate": { "total": 75.49212116800459, "count": 18192, "self": 75.49212116800459 } } }, "workers": { "total": 0.21642082501284676, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 454.1208797410095, "count": 18192, "is_parallel": true, "self": 236.53427957902477, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006440343999997822, "count": 1, "is_parallel": true, "self": 0.004304914000044846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021354299999529758, "count": 10, "is_parallel": true, "self": 0.0021354299999529758 } } }, "UnityEnvironment.step": { "total": 0.04053849399997489, "count": 1, "is_parallel": true, "self": 0.0006216089999497854, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044889100001910265, "count": 1, "is_parallel": true, "self": 0.00044889100001910265 }, "communicator.exchange": { "total": 0.037357896000003166, "count": 1, "is_parallel": true, "self": 0.037357896000003166 }, "steps_from_proto": { "total": 0.0021100980000028358, "count": 1, "is_parallel": true, "self": 0.0004139790000863286, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016961189999165072, "count": 10, "is_parallel": true, "self": 0.0016961189999165072 } } } } } } }, "UnityEnvironment.step": { "total": 217.58660016198473, "count": 18191, "is_parallel": true, "self": 10.208480756002132, "children": { "UnityEnvironment._generate_step_input": { "total": 5.85071898999945, "count": 18191, "is_parallel": true, "self": 5.85071898999945 }, "communicator.exchange": { "total": 167.19674589599128, "count": 18191, "is_parallel": true, "self": 167.19674589599128 }, "steps_from_proto": { "total": 34.33065451999187, "count": 18191, "is_parallel": true, "self": 6.120860472981235, "children": { "_process_rank_one_or_two_observation": { "total": 28.209794047010632, "count": 181910, "is_parallel": true, "self": 28.209794047010632 } } } } } } } } } } }, "trainer_advance": { "total": 126.76274855799761, "count": 18192, "self": 0.42636060099698625, "children": { "process_trajectory": { "total": 28.356888563000894, "count": 18192, "self": 27.87734287200078, "children": { "RLTrainer._checkpoint": { "total": 0.47954569100011213, "count": 4, "self": 0.47954569100011213 } } }, "_update_policy": { "total": 97.97949939399973, "count": 90, "self": 40.032805107003014, "children": { "TorchPPOOptimizer.update": { "total": 57.94669428699672, "count": 4587, "self": 57.94669428699672 } } } } } } }, "trainer_threads": { "total": 8.279998837679159e-07, "count": 1, "self": 8.279998837679159e-07 }, "TrainerController._save_models": { "total": 0.08449625899993407, "count": 1, "self": 0.0007947240001158207, "children": { "RLTrainer._checkpoint": { "total": 0.08370153499981825, "count": 1, "self": 0.08370153499981825 } } } } } } }