{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0135577917099, "min": 1.0135577917099, "max": 2.8526792526245117, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9710.8974609375, "min": 9710.8974609375, "max": 29277.046875, "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": 12.816375732421875, "min": 0.4256913363933563, "max": 12.816375732421875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.193359375, "min": 82.58412170410156, "max": 2586.05615234375, "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": 0.07111131593356891, "min": 0.06509591315461519, "max": 0.07504373932583713, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28444526373427564, "min": 0.26038365261846075, "max": 0.3604379053068959, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1988633451070271, "min": 0.12370077669894433, "max": 0.2931399298649208, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7954533804281084, "min": 0.4948031067957773, "max": 1.4656996493246042, "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": 25.568181818181817, "min": 3.659090909090909, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 161.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 3.659090909090909, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 161.0, "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": "1698326497", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698327094" }, "total": 596.7913543000001, "count": 1, "self": 0.7089389480000818, "children": { "run_training.setup": { "total": 0.057440418000055615, "count": 1, "self": 0.057440418000055615 }, "TrainerController.start_learning": { "total": 596.0249749339999, "count": 1, "self": 0.8693149770008404, "children": { "TrainerController._reset_env": { "total": 1.7950704020000785, "count": 1, "self": 1.7950704020000785 }, "TrainerController.advance": { "total": 593.204076545999, "count": 18207, "self": 0.4313962679887027, "children": { "env_step": { "total": 592.7726802780103, "count": 18207, "self": 469.21497762202637, "children": { "SubprocessEnvManager._take_step": { "total": 123.13693271199702, "count": 18207, "self": 2.2017706429996906, "children": { "TorchPolicy.evaluate": { "total": 120.93516206899733, "count": 18207, "self": 120.93516206899733 } } }, "workers": { "total": 0.4207699439868975, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 593.6774967560006, "count": 18207, "is_parallel": true, "self": 268.12109789598367, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006236931999978879, "count": 1, "is_parallel": true, "self": 0.003667735000021821, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025691969999570574, "count": 10, "is_parallel": true, "self": 0.0025691969999570574 } } }, "UnityEnvironment.step": { "total": 0.10007930799997666, "count": 1, "is_parallel": true, "self": 0.0007705119998036025, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004883620000555311, "count": 1, "is_parallel": true, "self": 0.0004883620000555311 }, "communicator.exchange": { "total": 0.09652596400007951, "count": 1, "is_parallel": true, "self": 0.09652596400007951 }, "steps_from_proto": { "total": 0.002294470000038018, "count": 1, "is_parallel": true, "self": 0.0005259770003931408, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017684929996448773, "count": 10, "is_parallel": true, "self": 0.0017684929996448773 } } } } } } }, "UnityEnvironment.step": { "total": 325.5563988600169, "count": 18206, "is_parallel": true, "self": 14.86346616499668, "children": { "UnityEnvironment._generate_step_input": { "total": 7.955930135013205, "count": 18206, "is_parallel": true, "self": 7.955930135013205 }, "communicator.exchange": { "total": 257.38433600400845, "count": 18206, "is_parallel": true, "self": 257.38433600400845 }, "steps_from_proto": { "total": 45.35266655599855, "count": 18206, "is_parallel": true, "self": 9.162785622989986, "children": { "_process_rank_one_or_two_observation": { "total": 36.18988093300857, "count": 182060, "is_parallel": true, "self": 36.18988093300857 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002888039998651948, "count": 1, "self": 0.0002888039998651948, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 588.0122727109995, "count": 623060, "is_parallel": true, "self": 13.75471757897401, "children": { "process_trajectory": { "total": 323.0654846910264, "count": 623060, "is_parallel": true, "self": 322.23441011602654, "children": { "RLTrainer._checkpoint": { "total": 0.8310745749998887, "count": 4, "is_parallel": true, "self": 0.8310745749998887 } } }, "_update_policy": { "total": 251.19207044099903, "count": 90, "is_parallel": true, "self": 73.3369774700044, "children": { "TorchPPOOptimizer.update": { "total": 177.85509297099463, "count": 4587, "is_parallel": true, "self": 177.85509297099463 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15622420500017142, "count": 1, "self": 0.002678310000192141, "children": { "RLTrainer._checkpoint": { "total": 0.15354589499997928, "count": 1, "self": 0.15354589499997928 } } } } } } }