{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8425408601760864, "min": 0.8333210349082947, "max": 2.8556642532348633, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8007.50830078125, "min": 8007.50830078125, "max": 29150.62109375, "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": 13.009675025939941, "min": 0.44209006428718567, "max": 13.023900985717773, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2536.88671875, "min": 85.76547241210938, "max": 2656.875732421875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06866713665116478, "min": 0.06029084135011277, "max": 0.07490552231080502, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2746685466046591, "min": 0.26268908951141046, "max": 0.37452761155402514, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1898124015652666, "min": 0.13292582105963913, "max": 0.29370032981330274, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7592496062610664, "min": 0.5317032842385565, "max": 1.4148840249753465, "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": 25.59090909090909, "min": 3.727272727272727, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 164.0, "max": 1414.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.727272727272727, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 164.0, "max": 1414.0, "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": "1750767877", "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": "1750768310" }, "total": 433.28806390700004, "count": 1, "self": 0.44281158700016476, "children": { "run_training.setup": { "total": 0.022799109999937173, "count": 1, "self": 0.022799109999937173 }, "TrainerController.start_learning": { "total": 432.82245320999994, "count": 1, "self": 0.40078265199520047, "children": { "TrainerController._reset_env": { "total": 3.044001550999951, "count": 1, "self": 3.044001550999951 }, "TrainerController.advance": { "total": 429.29088385500484, "count": 18192, "self": 0.40997372900551454, "children": { "env_step": { "total": 309.95667869300485, "count": 18192, "self": 238.32714206299545, "children": { "SubprocessEnvManager._take_step": { "total": 71.39517242400632, "count": 18192, "self": 1.297087757009649, "children": { "TorchPolicy.evaluate": { "total": 70.09808466699667, "count": 18192, "self": 70.09808466699667 } } }, "workers": { "total": 0.23436420600307883, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 431.3704934610088, "count": 18192, "is_parallel": true, "self": 222.7075333600162, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0050663339999346135, "count": 1, "is_parallel": true, "self": 0.003660674000002473, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014056599999321406, "count": 10, "is_parallel": true, "self": 0.0014056599999321406 } } }, "UnityEnvironment.step": { "total": 0.036294650999934674, "count": 1, "is_parallel": true, "self": 0.0006230669997648874, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004351890000862113, "count": 1, "is_parallel": true, "self": 0.0004351890000862113 }, "communicator.exchange": { "total": 0.03331347300002108, "count": 1, "is_parallel": true, "self": 0.03331347300002108 }, "steps_from_proto": { "total": 0.0019229220000624991, "count": 1, "is_parallel": true, "self": 0.00034902400022929214, "children": { "_process_rank_one_or_two_observation": { "total": 0.001573897999833207, "count": 10, "is_parallel": true, "self": 0.001573897999833207 } } } } } } }, "UnityEnvironment.step": { "total": 208.66296010099256, "count": 18191, "is_parallel": true, "self": 9.713693203978892, "children": { "UnityEnvironment._generate_step_input": { "total": 5.468125406003537, "count": 18191, "is_parallel": true, "self": 5.468125406003537 }, "communicator.exchange": { "total": 161.5661902600026, "count": 18191, "is_parallel": true, "self": 161.5661902600026 }, "steps_from_proto": { "total": 31.914951231007535, "count": 18191, "is_parallel": true, "self": 5.765331033012217, "children": { "_process_rank_one_or_two_observation": { "total": 26.14962019799532, "count": 181910, "is_parallel": true, "self": 26.14962019799532 } } } } } } } } } } }, "trainer_advance": { "total": 118.92423143299447, "count": 18192, "self": 0.4975211619982929, "children": { "process_trajectory": { "total": 25.78356902299663, "count": 18192, "self": 25.32723263299647, "children": { "RLTrainer._checkpoint": { "total": 0.45633639000016046, "count": 4, "self": 0.45633639000016046 } } }, "_update_policy": { "total": 92.64314124799955, "count": 90, "self": 38.05080868900086, "children": { "TorchPPOOptimizer.update": { "total": 54.59233255899869, "count": 4587, "self": 54.59233255899869 } } } } } } }, "trainer_threads": { "total": 1.0109999948326731e-06, "count": 1, "self": 1.0109999948326731e-06 }, "TrainerController._save_models": { "total": 0.0867841409999528, "count": 1, "self": 0.0008416519999627781, "children": { "RLTrainer._checkpoint": { "total": 0.08594248899999002, "count": 1, "self": 0.08594248899999002 } } } } } } }