{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8299292325973511, "min": 0.8299292325973511, "max": 2.8554718494415283, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7887.6474609375, "min": 7887.6474609375, "max": 29148.65625, "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": 13.189594268798828, "min": 0.3819257616996765, "max": 13.189594268798828, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2571.970947265625, "min": 74.09359741210938, "max": 2680.6767578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07031646201514877, "min": 0.061551770040429846, "max": 0.07479127798864034, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28126584806059507, "min": 0.24620708016171938, "max": 0.3739563899432017, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19327427571018535, "min": 0.10991183994452049, "max": 0.2841788329330145, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7730971028407414, "min": 0.43964735977808195, "max": 1.4208941646650723, "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": 25.727272727272727, "min": 2.9318181818181817, "max": 26.181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 129.0, "max": 1438.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 2.9318181818181817, "max": 26.181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 129.0, "max": 1438.0, "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": "1749122101", "python_version": "3.10.12 (main, May 22 2025, 18:49:42) [GCC 9.4.0]", "command_line_arguments": "/root/.pyenv/versions/3.10.12/envs/mlagents-env/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": "1749122260" }, "total": 158.38986877293792, "count": 1, "self": 0.16724044200964272, "children": { "run_training.setup": { "total": 0.016164758941158652, "count": 1, "self": 0.016164758941158652 }, "TrainerController.start_learning": { "total": 158.20646357198711, "count": 1, "self": 0.1431004317710176, "children": { "TrainerController._reset_env": { "total": 1.914624890894629, "count": 1, "self": 1.914624890894629 }, "TrainerController.advance": { "total": 156.1133618853055, "count": 18192, "self": 0.13858608715236187, "children": { "env_step": { "total": 101.26742241438478, "count": 18192, "self": 76.0757377455011, "children": { "SubprocessEnvManager._take_step": { "total": 25.098684908356518, "count": 18192, "self": 0.48844951146747917, "children": { "TorchPolicy.evaluate": { "total": 24.61023539688904, "count": 18192, "self": 24.61023539688904 } } }, "workers": { "total": 0.09299976052716374, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 157.9129306615796, "count": 18192, "is_parallel": true, "self": 91.64295803371351, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012749680317938328, "count": 1, "is_parallel": true, "self": 0.00032346684020012617, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009515011915937066, "count": 10, "is_parallel": true, "self": 0.0009515011915937066 } } }, "UnityEnvironment.step": { "total": 0.012433732044883072, "count": 1, "is_parallel": true, "self": 0.00020180700812488794, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019233999773859978, "count": 1, "is_parallel": true, "self": 0.00019233999773859978 }, "communicator.exchange": { "total": 0.011341467034071684, "count": 1, "is_parallel": true, "self": 0.011341467034071684 }, "steps_from_proto": { "total": 0.0006981180049479008, "count": 1, "is_parallel": true, "self": 0.00016019982285797596, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005379181820899248, "count": 10, "is_parallel": true, "self": 0.0005379181820899248 } } } } } } }, "UnityEnvironment.step": { "total": 66.26997262786608, "count": 18191, "is_parallel": true, "self": 2.2677709638373926, "children": { "UnityEnvironment._generate_step_input": { "total": 1.5655268728733063, "count": 18191, "is_parallel": true, "self": 1.5655268728733063 }, "communicator.exchange": { "total": 54.77159842418041, "count": 18191, "is_parallel": true, "self": 54.77159842418041 }, "steps_from_proto": { "total": 7.665076366974972, "count": 18191, "is_parallel": true, "self": 1.4689645586768165, "children": { "_process_rank_one_or_two_observation": { "total": 6.196111808298156, "count": 181910, "is_parallel": true, "self": 6.196111808298156 } } } } } } } } } } }, "trainer_advance": { "total": 54.70735338376835, "count": 18192, "self": 0.15825485822279006, "children": { "process_trajectory": { "total": 11.975584443891421, "count": 18192, "self": 11.730555018992163, "children": { "RLTrainer._checkpoint": { "total": 0.24502942489925772, "count": 4, "self": 0.24502942489925772 } } }, "_update_policy": { "total": 42.57351408165414, "count": 90, "self": 21.889681979781017, "children": { "TorchPPOOptimizer.update": { "total": 20.683832101873122, "count": 4587, "self": 20.683832101873122 } } } } } } }, "trainer_threads": { "total": 6.320187821984291e-07, "count": 1, "self": 6.320187821984291e-07 }, "TrainerController._save_models": { "total": 0.035375731997191906, "count": 1, "self": 0.00048288400284945965, "children": { "RLTrainer._checkpoint": { "total": 0.034892847994342446, "count": 1, "self": 0.034892847994342446 } } } } } } }