{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0260181427001953, "min": 1.0260181427001953, "max": 2.8492064476013184, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9830.2802734375, "min": 9830.2802734375, "max": 29241.40625, "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": 12.225529670715332, "min": 0.2610379457473755, "max": 12.225529670715332, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2383.978271484375, "min": 50.641361236572266, "max": 2460.5400390625, "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.Losses.PolicyLoss.mean": { "value": 0.06649353756538226, "min": 0.06079165873610799, "max": 0.07567304706340199, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26597415026152904, "min": 0.258229916199329, "max": 0.37836523531700994, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20006445769731906, "min": 0.11048052128970476, "max": 0.29518860096440597, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8002578307892763, "min": 0.44192208515881903, "max": 1.394432828414674, "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.CumulativeReward.mean": { "value": 23.568181818181817, "min": 3.227272727272727, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1037.0, "min": 142.0, "max": 1314.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.568181818181817, "min": 3.227272727272727, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1037.0, "min": 142.0, "max": 1314.0, "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": "1703821824", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703822410" }, "total": 585.6417612540001, "count": 1, "self": 0.544675993000169, "children": { "run_training.setup": { "total": 0.07149127499997121, "count": 1, "self": 0.07149127499997121 }, "TrainerController.start_learning": { "total": 585.025593986, "count": 1, "self": 0.8422403949998625, "children": { "TrainerController._reset_env": { "total": 4.400702438999929, "count": 1, "self": 4.400702438999929 }, "TrainerController.advance": { "total": 579.6784358980001, "count": 18203, "self": 0.4465639099911414, "children": { "env_step": { "total": 579.231871988009, "count": 18203, "self": 452.69884230801574, "children": { "SubprocessEnvManager._take_step": { "total": 126.12675425400255, "count": 18203, "self": 2.454784062013914, "children": { "TorchPolicy.evaluate": { "total": 123.67197019198863, "count": 18203, "self": 123.67197019198863 } } }, "workers": { "total": 0.4062754259906569, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 582.8747366660185, "count": 18203, "is_parallel": true, "self": 268.10960841701296, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00725013199996738, "count": 1, "is_parallel": true, "self": 0.0052265269999907105, "children": { "_process_rank_one_or_two_observation": { "total": 0.002023604999976669, "count": 10, "is_parallel": true, "self": 0.002023604999976669 } } }, "UnityEnvironment.step": { "total": 0.04675220399997215, "count": 1, "is_parallel": true, "self": 0.0006987089999483942, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004565680000041539, "count": 1, "is_parallel": true, "self": 0.0004565680000041539 }, "communicator.exchange": { "total": 0.04345763000003444, "count": 1, "is_parallel": true, "self": 0.04345763000003444 }, "steps_from_proto": { "total": 0.002139296999985163, "count": 1, "is_parallel": true, "self": 0.00042822300019906834, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017110739997860946, "count": 10, "is_parallel": true, "self": 0.0017110739997860946 } } } } } } }, "UnityEnvironment.step": { "total": 314.76512824900556, "count": 18202, "is_parallel": true, "self": 15.296865830998854, "children": { "UnityEnvironment._generate_step_input": { "total": 7.564070324997147, "count": 18202, "is_parallel": true, "self": 7.564070324997147 }, "communicator.exchange": { "total": 247.02114556300796, "count": 18202, "is_parallel": true, "self": 247.02114556300796 }, "steps_from_proto": { "total": 44.88304653000159, "count": 18202, "is_parallel": true, "self": 8.872871600964345, "children": { "_process_rank_one_or_two_observation": { "total": 36.01017492903725, "count": 182020, "is_parallel": true, "self": 36.01017492903725 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016321800012519816, "count": 1, "self": 0.00016321800012519816, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 572.5672028480466, "count": 766446, "is_parallel": true, "self": 18.273120908029796, "children": { "process_trajectory": { "total": 312.55070729501756, "count": 766446, "is_parallel": true, "self": 311.78318865901747, "children": { "RLTrainer._checkpoint": { "total": 0.7675186360000907, "count": 4, "is_parallel": true, "self": 0.7675186360000907 } } }, "_update_policy": { "total": 241.74337464499922, "count": 90, "is_parallel": true, "self": 71.16097788599848, "children": { "TorchPPOOptimizer.update": { "total": 170.58239675900074, "count": 4587, "is_parallel": true, "self": 170.58239675900074 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10405203599998458, "count": 1, "self": 0.0014987130000463367, "children": { "RLTrainer._checkpoint": { "total": 0.10255332299993825, "count": 1, "self": 0.10255332299993825 } } } } } } }