{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8220953345298767, "min": 0.8027382493019104, "max": 2.840188980102539, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7813.1943359375, "min": 7813.1943359375, "max": 28992.6484375, "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": 12.89062786102295, "min": 0.414014607667923, "max": 12.89062786102295, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2513.67236328125, "min": 80.31883239746094, "max": 2611.201171875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06066169503552088, "min": 0.06066169503552088, "max": 0.071305192033298, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24264678014208352, "min": 0.24264678014208352, "max": 0.3542073448120123, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19240607211694996, "min": 0.1392214302014669, "max": 0.29073013927714497, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7696242884677998, "min": 0.5568857208058676, "max": 1.4193046148501192, "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": 25.613636363636363, "min": 4.045454545454546, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 178.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 4.045454545454546, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 178.0, "max": 1405.0, "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": "1742980210", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/samrito/anaconda3/envs/drl_hf/bin/mlagents-learn ./SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1742980355" }, "total": 144.3871225558687, "count": 1, "self": 0.1670380316209048, "children": { "run_training.setup": { "total": 0.010089769028127193, "count": 1, "self": 0.010089769028127193 }, "TrainerController.start_learning": { "total": 144.20999475521967, "count": 1, "self": 0.1513604132924229, "children": { "TrainerController._reset_env": { "total": 0.8655625542160124, "count": 1, "self": 0.8655625542160124 }, "TrainerController.advance": { "total": 143.1615267638117, "count": 18192, "self": 0.14614993729628623, "children": { "env_step": { "total": 101.28089773003012, "count": 18192, "self": 77.994337847922, "children": { "SubprocessEnvManager._take_step": { "total": 23.192705842200667, "count": 18192, "self": 0.5426033262629062, "children": { "TorchPolicy.evaluate": { "total": 22.65010251593776, "count": 18192, "self": 22.65010251593776 } } }, "workers": { "total": 0.09385403990745544, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 143.84897279483266, "count": 18192, "is_parallel": true, "self": 76.22699280409142, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008266360964626074, "count": 1, "is_parallel": true, "self": 0.00022962410002946854, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005970119964331388, "count": 10, "is_parallel": true, "self": 0.0005970119964331388 } } }, "UnityEnvironment.step": { "total": 0.012576231034472585, "count": 1, "is_parallel": true, "self": 0.00023218197748064995, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00012792600318789482, "count": 1, "is_parallel": true, "self": 0.00012792600318789482 }, "communicator.exchange": { "total": 0.011745691997930408, "count": 1, "is_parallel": true, "self": 0.011745691997930408 }, "steps_from_proto": { "total": 0.00047043105587363243, "count": 1, "is_parallel": true, "self": 0.00010659522376954556, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003638358321040869, "count": 10, "is_parallel": true, "self": 0.0003638358321040869 } } } } } } }, "UnityEnvironment.step": { "total": 67.62197999074124, "count": 18191, "is_parallel": true, "self": 2.6838127102237195, "children": { "UnityEnvironment._generate_step_input": { "total": 1.290543596725911, "count": 18191, "is_parallel": true, "self": 1.290543596725911 }, "communicator.exchange": { "total": 56.16848181770183, "count": 18191, "is_parallel": true, "self": 56.16848181770183 }, "steps_from_proto": { "total": 7.479141866089776, "count": 18191, "is_parallel": true, "self": 1.5059493624139577, "children": { "_process_rank_one_or_two_observation": { "total": 5.973192503675818, "count": 181910, "is_parallel": true, "self": 5.973192503675818 } } } } } } } } } } }, "trainer_advance": { "total": 41.7344790964853, "count": 18192, "self": 0.17673324467614293, "children": { "process_trajectory": { "total": 9.766545257763937, "count": 18192, "self": 9.553736860863864, "children": { "RLTrainer._checkpoint": { "total": 0.2128083969000727, "count": 4, "self": 0.2128083969000727 } } }, "_update_policy": { "total": 31.791200594045222, "count": 90, "self": 13.27342741121538, "children": { "TorchPPOOptimizer.update": { "total": 18.517773182829842, "count": 4587, "self": 18.517773182829842 } } } } } } }, "trainer_threads": { "total": 6.51925802230835e-07, "count": 1, "self": 6.51925802230835e-07 }, "TrainerController._save_models": { "total": 0.03154437197372317, "count": 1, "self": 0.0005378869827836752, "children": { "RLTrainer._checkpoint": { "total": 0.031006484990939498, "count": 1, "self": 0.031006484990939498 } } } } } } }