{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8905409574508667, "min": 0.8905409574508667, "max": 2.8400042057037354, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8463.701171875, "min": 8463.701171875, "max": 28990.76171875, "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": 12.701868057250977, "min": 0.3789485991001129, "max": 12.701868057250977, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2476.8642578125, "min": 73.51602935791016, "max": 2570.07958984375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06806137490739096, "min": 0.06383012022649615, "max": 0.07634170381808836, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27224549962956385, "min": 0.2597947188312937, "max": 0.3817085190904418, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18767397901883312, "min": 0.13160923496116977, "max": 0.29142710473023203, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7506959160753325, "min": 0.5264369398446791, "max": 1.4571355236511603, "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": 25.272727272727273, "min": 3.522727272727273, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 155.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.522727272727273, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 155.0, "max": 1378.0, "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": "1743007109", "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 --force --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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743007591" }, "total": 482.2777188460002, "count": 1, "self": 0.683742597000446, "children": { "run_training.setup": { "total": 0.023191210000049978, "count": 1, "self": 0.023191210000049978 }, "TrainerController.start_learning": { "total": 481.5707850389997, "count": 1, "self": 0.42094103900467417, "children": { "TrainerController._reset_env": { "total": 2.028618442999914, "count": 1, "self": 2.028618442999914 }, "TrainerController.advance": { "total": 478.96575057199493, "count": 18192, "self": 0.428196934989046, "children": { "env_step": { "total": 345.26993485199, "count": 18192, "self": 261.8257360730113, "children": { "SubprocessEnvManager._take_step": { "total": 83.19201628598239, "count": 18192, "self": 1.446629362997328, "children": { "TorchPolicy.evaluate": { "total": 81.74538692298506, "count": 18192, "self": 81.74538692298506 } } }, "workers": { "total": 0.2521824929963259, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 479.7171606940178, "count": 18192, "is_parallel": true, "self": 249.9773349130228, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002689557000167042, "count": 1, "is_parallel": true, "self": 0.0008511099999850558, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018384470001819864, "count": 10, "is_parallel": true, "self": 0.0018384470001819864 } } }, "UnityEnvironment.step": { "total": 0.04018994400007614, "count": 1, "is_parallel": true, "self": 0.0006676779998997517, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041848799992294516, "count": 1, "is_parallel": true, "self": 0.00041848799992294516 }, "communicator.exchange": { "total": 0.03682130300012432, "count": 1, "is_parallel": true, "self": 0.03682130300012432 }, "steps_from_proto": { "total": 0.002282475000129125, "count": 1, "is_parallel": true, "self": 0.0004187990000446007, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018636760000845243, "count": 10, "is_parallel": true, "self": 0.0018636760000845243 } } } } } } }, "UnityEnvironment.step": { "total": 229.73982578099503, "count": 18191, "is_parallel": true, "self": 10.737524576998794, "children": { "UnityEnvironment._generate_step_input": { "total": 6.207373099995493, "count": 18191, "is_parallel": true, "self": 6.207373099995493 }, "communicator.exchange": { "total": 176.75459033000607, "count": 18191, "is_parallel": true, "self": 176.75459033000607 }, "steps_from_proto": { "total": 36.04033777399468, "count": 18191, "is_parallel": true, "self": 6.523646322943478, "children": { "_process_rank_one_or_two_observation": { "total": 29.5166914510512, "count": 181910, "is_parallel": true, "self": 29.5166914510512 } } } } } } } } } } }, "trainer_advance": { "total": 133.26761878501588, "count": 18192, "self": 0.5541339770302329, "children": { "process_trajectory": { "total": 29.672277373985935, "count": 18192, "self": 28.95469281598571, "children": { "RLTrainer._checkpoint": { "total": 0.717584558000226, "count": 4, "self": 0.717584558000226 } } }, "_update_policy": { "total": 103.04120743399972, "count": 90, "self": 41.36137749099112, "children": { "TorchPPOOptimizer.update": { "total": 61.6798299430086, "count": 4587, "self": 61.6798299430086 } } } } } } }, "trainer_threads": { "total": 1.2450000212993473e-06, "count": 1, "self": 1.2450000212993473e-06 }, "TrainerController._save_models": { "total": 0.15547374000016134, "count": 1, "self": 0.0013373750002756424, "children": { "RLTrainer._checkpoint": { "total": 0.1541363649998857, "count": 1, "self": 0.1541363649998857 } } } } } } }