{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0959607362747192, "min": 1.0959607362747192, "max": 2.875150203704834, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10488.34375, "min": 10488.34375, "max": 29444.4140625, "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": 12.23735523223877, "min": 0.4488576650619507, "max": 12.23735523223877, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2386.2841796875, "min": 87.07838439941406, "max": 2462.1396484375, "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": 0.07203512930159466, "min": 0.0636595141674893, "max": 0.07455484234564139, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2881405172063786, "min": 0.2546380566699572, "max": 0.35530378060260165, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2056429760859293, "min": 0.1089419614952788, "max": 0.2702687812202117, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8225719043437172, "min": 0.4357678459811152, "max": 1.3513439061010586, "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": 24.113636363636363, "min": 3.090909090909091, "max": 24.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1061.0, "min": 136.0, "max": 1318.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.113636363636363, "min": 3.090909090909091, "max": 24.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1061.0, "min": 136.0, "max": 1318.0, "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": "1689068018", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689068524" }, "total": 506.080901154, "count": 1, "self": 0.8398902989999897, "children": { "run_training.setup": { "total": 0.04374991900002101, "count": 1, "self": 0.04374991900002101 }, "TrainerController.start_learning": { "total": 505.19726093599996, "count": 1, "self": 0.6544228090089632, "children": { "TrainerController._reset_env": { "total": 4.222750880000007, "count": 1, "self": 4.222750880000007 }, "TrainerController.advance": { "total": 500.091667978991, "count": 18222, "self": 0.33914573901057565, "children": { "env_step": { "total": 499.7525222399804, "count": 18222, "self": 363.7305633309811, "children": { "SubprocessEnvManager._take_step": { "total": 135.70233363000008, "count": 18222, "self": 2.0011912100040377, "children": { "TorchPolicy.evaluate": { "total": 133.70114241999605, "count": 18222, "self": 133.70114241999605 } } }, "workers": { "total": 0.31962527899924, "count": 18222, "self": 0.0, "children": { "worker_root": { "total": 503.1889488570089, "count": 18222, "is_parallel": true, "self": 233.73887496101077, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005892208000005894, "count": 1, "is_parallel": true, "self": 0.004393414000048779, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014987939999571154, "count": 10, "is_parallel": true, "self": 0.0014987939999571154 } } }, "UnityEnvironment.step": { "total": 0.07566489500001694, "count": 1, "is_parallel": true, "self": 0.0006428050000408803, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004057200000033845, "count": 1, "is_parallel": true, "self": 0.0004057200000033845 }, "communicator.exchange": { "total": 0.07239563299998508, "count": 1, "is_parallel": true, "self": 0.07239563299998508 }, "steps_from_proto": { "total": 0.0022207369999875937, "count": 1, "is_parallel": true, "self": 0.0004976280000050792, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017231089999825144, "count": 10, "is_parallel": true, "self": 0.0017231089999825144 } } } } } } }, "UnityEnvironment.step": { "total": 269.4500738959981, "count": 18221, "is_parallel": true, "self": 11.074867502989832, "children": { "UnityEnvironment._generate_step_input": { "total": 5.662263118004006, "count": 18221, "is_parallel": true, "self": 5.662263118004006 }, "communicator.exchange": { "total": 214.63421695499844, "count": 18221, "is_parallel": true, "self": 214.63421695499844 }, "steps_from_proto": { "total": 38.07872632000587, "count": 18221, "is_parallel": true, "self": 7.044027782979839, "children": { "_process_rank_one_or_two_observation": { "total": 31.03469853702603, "count": 182210, "is_parallel": true, "self": 31.03469853702603 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.908200001973455e-05, "count": 1, "self": 9.908200001973455e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 496.12000840602, "count": 489580, "is_parallel": true, "self": 10.766208043002962, "children": { "process_trajectory": { "total": 274.0796417010176, "count": 489580, "is_parallel": true, "self": 271.3465050630175, "children": { "RLTrainer._checkpoint": { "total": 2.733136638000076, "count": 4, "is_parallel": true, "self": 2.733136638000076 } } }, "_update_policy": { "total": 211.27415866199948, "count": 90, "is_parallel": true, "self": 80.55410754899813, "children": { "TorchPPOOptimizer.update": { "total": 130.72005111300135, "count": 4584, "is_parallel": true, "self": 130.72005111300135 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22832018600001902, "count": 1, "self": 0.0012200020000818768, "children": { "RLTrainer._checkpoint": { "total": 0.22710018399993714, "count": 1, "self": 0.22710018399993714 } } } } } } }