{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0179892778396606, "min": 1.0179892778396606, "max": 2.85776948928833, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9719.76171875, "min": 9719.76171875, "max": 29329.287109375, "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": 13.004942893981934, "min": 0.4362665116786957, "max": 13.004942893981934, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2535.9638671875, "min": 84.63570404052734, "max": 2638.45458984375, "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": 0.06741823021958207, "min": 0.06120186416108695, "max": 0.07387114492873889, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2696729208783283, "min": 0.256668856392578, "max": 0.35081164845934265, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19488527669626124, "min": 0.11660115955986411, "max": 0.29476525771851636, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.779541106785045, "min": 0.46640463823945644, "max": 1.4738262885925817, "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": 26.09090909090909, "min": 3.2045454545454546, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1148.0, "min": 141.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.09090909090909, "min": 3.2045454545454546, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1148.0, "min": 141.0, "max": 1415.0, "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": "1692382671", "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": "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": "1692383161" }, "total": 489.705433535, "count": 1, "self": 0.432066561000056, "children": { "run_training.setup": { "total": 0.041484606999972584, "count": 1, "self": 0.041484606999972584 }, "TrainerController.start_learning": { "total": 489.23188236699997, "count": 1, "self": 0.544816770996988, "children": { "TrainerController._reset_env": { "total": 4.053533125000001, "count": 1, "self": 4.053533125000001 }, "TrainerController.advance": { "total": 484.48484906800303, "count": 18201, "self": 0.3021994190059445, "children": { "env_step": { "total": 484.1826496489971, "count": 18201, "self": 353.5157727140062, "children": { "SubprocessEnvManager._take_step": { "total": 130.36892388500155, "count": 18201, "self": 1.8703251600012436, "children": { "TorchPolicy.evaluate": { "total": 128.4985987250003, "count": 18201, "self": 128.4985987250003 } } }, "workers": { "total": 0.2979530499893599, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 487.5788746749882, "count": 18201, "is_parallel": true, "self": 228.93199992397967, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007256449000010434, "count": 1, "is_parallel": true, "self": 0.0053305819999422965, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019258670000681377, "count": 10, "is_parallel": true, "self": 0.0019258670000681377 } } }, "UnityEnvironment.step": { "total": 0.05098485799999253, "count": 1, "is_parallel": true, "self": 0.0006579039999792258, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003821949999860408, "count": 1, "is_parallel": true, "self": 0.0003821949999860408 }, "communicator.exchange": { "total": 0.04754450299998325, "count": 1, "is_parallel": true, "self": 0.04754450299998325 }, "steps_from_proto": { "total": 0.00240025600004401, "count": 1, "is_parallel": true, "self": 0.00041142399982163624, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019888320002223736, "count": 10, "is_parallel": true, "self": 0.0019888320002223736 } } } } } } }, "UnityEnvironment.step": { "total": 258.6468747510085, "count": 18200, "is_parallel": true, "self": 10.838097016004951, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5540817349947815, "count": 18200, "is_parallel": true, "self": 5.5540817349947815 }, "communicator.exchange": { "total": 203.5650991590045, "count": 18200, "is_parallel": true, "self": 203.5650991590045 }, "steps_from_proto": { "total": 38.68959684100429, "count": 18200, "is_parallel": true, "self": 7.1416963569975, "children": { "_process_rank_one_or_two_observation": { "total": 31.54790048400679, "count": 182000, "is_parallel": true, "self": 31.54790048400679 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019618900000750727, "count": 1, "self": 0.00019618900000750727, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 480.52301941500156, "count": 458077, "is_parallel": true, "self": 10.556137560041805, "children": { "process_trajectory": { "total": 265.98348330596014, "count": 458077, "is_parallel": true, "self": 264.67665535996025, "children": { "RLTrainer._checkpoint": { "total": 1.3068279459998848, "count": 4, "is_parallel": true, "self": 1.3068279459998848 } } }, "_update_policy": { "total": 203.98339854899962, "count": 90, "is_parallel": true, "self": 82.02266429000076, "children": { "TorchPPOOptimizer.update": { "total": 121.96073425899885, "count": 4587, "is_parallel": true, "self": 121.96073425899885 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14848721399994247, "count": 1, "self": 0.0008864269998412055, "children": { "RLTrainer._checkpoint": { "total": 0.14760078700010126, "count": 1, "self": 0.14760078700010126 } } } } } } }