{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9338843822479248, "min": 0.9246625304222107, "max": 2.869049072265625, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8937.2734375, "min": 8937.2734375, "max": 29539.73046875, "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": 12.957916259765625, "min": 0.3487296402454376, "max": 12.957916259765625, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.793701171875, "min": 67.65354919433594, "max": 2641.10546875, "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": 0.06528911886476528, "min": 0.06409212879804602, "max": 0.07897743465397142, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2611564754590611, "min": 0.2575629533140255, "max": 0.38870086635841866, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.209516745279817, "min": 0.12109585805093029, "max": 0.27738563489972373, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.838066981119268, "min": 0.48438343220372115, "max": 1.3327181570085824, "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": 25.181818181818183, "min": 3.522727272727273, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 155.0, "max": 1424.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 3.522727272727273, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 155.0, "max": 1424.0, "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": "1698948572", "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": "1698949033" }, "total": 461.5100601070001, "count": 1, "self": 0.43493483900005003, "children": { "run_training.setup": { "total": 0.04397147800000312, "count": 1, "self": 0.04397147800000312 }, "TrainerController.start_learning": { "total": 461.03115379, "count": 1, "self": 0.5561855709942733, "children": { "TrainerController._reset_env": { "total": 8.966077282000015, "count": 1, "self": 8.966077282000015 }, "TrainerController.advance": { "total": 451.4268449490056, "count": 18200, "self": 0.2672975099964674, "children": { "env_step": { "total": 451.15954743900915, "count": 18200, "self": 310.06958262700914, "children": { "SubprocessEnvManager._take_step": { "total": 140.80741077300013, "count": 18200, "self": 1.3994534189950514, "children": { "TorchPolicy.evaluate": { "total": 139.40795735400508, "count": 18200, "self": 139.40795735400508 } } }, "workers": { "total": 0.2825540389998764, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 459.8961163700061, "count": 18200, "is_parallel": true, "self": 223.2641001880109, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005531608999945092, "count": 1, "is_parallel": true, "self": 0.004159812000068541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013717969998765511, "count": 10, "is_parallel": true, "self": 0.0013717969998765511 } } }, "UnityEnvironment.step": { "total": 0.039867620999984865, "count": 1, "is_parallel": true, "self": 0.0006611969999994471, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000393238000015117, "count": 1, "is_parallel": true, "self": 0.000393238000015117 }, "communicator.exchange": { "total": 0.03701986099997612, "count": 1, "is_parallel": true, "self": 0.03701986099997612 }, "steps_from_proto": { "total": 0.0017933249999941836, "count": 1, "is_parallel": true, "self": 0.00033935499999415697, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014539700000000266, "count": 10, "is_parallel": true, "self": 0.0014539700000000266 } } } } } } }, "UnityEnvironment.step": { "total": 236.6320161819952, "count": 18199, "is_parallel": true, "self": 10.309147519005137, "children": { "UnityEnvironment._generate_step_input": { "total": 5.28341964599548, "count": 18199, "is_parallel": true, "self": 5.28341964599548 }, "communicator.exchange": { "total": 187.9718974139921, "count": 18199, "is_parallel": true, "self": 187.9718974139921 }, "steps_from_proto": { "total": 33.06755160300247, "count": 18199, "is_parallel": true, "self": 6.248114703988165, "children": { "_process_rank_one_or_two_observation": { "total": 26.819436899014306, "count": 181990, "is_parallel": true, "self": 26.819436899014306 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012499100000695762, "count": 1, "self": 0.00012499100000695762, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 447.73622631601324, "count": 459911, "is_parallel": true, "self": 9.67340884800592, "children": { "process_trajectory": { "total": 253.153616145007, "count": 459911, "is_parallel": true, "self": 252.41463330400694, "children": { "RLTrainer._checkpoint": { "total": 0.7389828410000518, "count": 4, "is_parallel": true, "self": 0.7389828410000518 } } }, "_update_policy": { "total": 184.90920132300033, "count": 90, "is_parallel": true, "self": 53.863017876998015, "children": { "TorchPPOOptimizer.update": { "total": 131.04618344600232, "count": 4587, "is_parallel": true, "self": 131.04618344600232 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08192099700011113, "count": 1, "self": 0.0008848240000816077, "children": { "RLTrainer._checkpoint": { "total": 0.08103617300002952, "count": 1, "self": 0.08103617300002952 } } } } } } }