{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0120735168457031, "min": 1.0080653429031372, "max": 2.872229814529419, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9685.5439453125, "min": 9685.5439453125, "max": 29446.099609375, "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": 13.026284217834473, "min": 0.44540831446647644, "max": 13.026284217834473, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.12548828125, "min": 86.40921020507812, "max": 2624.58837890625, "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": 0.07476808296461754, "min": 0.059720667887378634, "max": 0.07476808296461754, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29907233185847015, "min": 0.24913353945385988, "max": 0.3629118425996435, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20969220922858103, "min": 0.11745816001705095, "max": 0.28403869351627775, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8387688369143241, "min": 0.4698326400682038, "max": 1.3585399275316912, "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": 25.772727272727273, "min": 3.6818181818181817, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 162.0, "max": 1410.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.6818181818181817, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 162.0, "max": 1410.0, "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": "1724470255", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724470818" }, "total": 562.5829389090001, "count": 1, "self": 0.5871822160000875, "children": { "run_training.setup": { "total": 0.09935355900000786, "count": 1, "self": 0.09935355900000786 }, "TrainerController.start_learning": { "total": 561.896403134, "count": 1, "self": 0.788713293005344, "children": { "TrainerController._reset_env": { "total": 3.508839935000026, "count": 1, "self": 3.508839935000026 }, "TrainerController.advance": { "total": 557.503648118995, "count": 18204, "self": 0.3918559649936242, "children": { "env_step": { "total": 557.1117921540014, "count": 18204, "self": 429.37635880901485, "children": { "SubprocessEnvManager._take_step": { "total": 127.31907339799687, "count": 18204, "self": 2.119076345990777, "children": { "TorchPolicy.evaluate": { "total": 125.1999970520061, "count": 18204, "self": 125.1999970520061 } } }, "workers": { "total": 0.41635994698964396, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 560.1768444219964, "count": 18204, "is_parallel": true, "self": 261.06051842498886, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007090554000001248, "count": 1, "is_parallel": true, "self": 0.004407014999912917, "children": { "_process_rank_one_or_two_observation": { "total": 0.002683539000088331, "count": 10, "is_parallel": true, "self": 0.002683539000088331 } } }, "UnityEnvironment.step": { "total": 0.04337497799997436, "count": 1, "is_parallel": true, "self": 0.0008166810000602709, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004598559999635654, "count": 1, "is_parallel": true, "self": 0.0004598559999635654 }, "communicator.exchange": { "total": 0.03984051800000543, "count": 1, "is_parallel": true, "self": 0.03984051800000543 }, "steps_from_proto": { "total": 0.0022579229999450945, "count": 1, "is_parallel": true, "self": 0.0004186719999097477, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018392510000353468, "count": 10, "is_parallel": true, "self": 0.0018392510000353468 } } } } } } }, "UnityEnvironment.step": { "total": 299.11632599700755, "count": 18203, "is_parallel": true, "self": 14.315836396017232, "children": { "UnityEnvironment._generate_step_input": { "total": 7.1346272899972405, "count": 18203, "is_parallel": true, "self": 7.1346272899972405 }, "communicator.exchange": { "total": 234.18766361299868, "count": 18203, "is_parallel": true, "self": 234.18766361299868 }, "steps_from_proto": { "total": 43.4781986979944, "count": 18203, "is_parallel": true, "self": 8.400747637058032, "children": { "_process_rank_one_or_two_observation": { "total": 35.07745106093637, "count": 182030, "is_parallel": true, "self": 35.07745106093637 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015343899985964526, "count": 1, "self": 0.00015343899985964526, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 551.0205913539821, "count": 761158, "is_parallel": true, "self": 16.620038676997183, "children": { "process_trajectory": { "total": 299.95984513598535, "count": 761158, "is_parallel": true, "self": 298.8608982549854, "children": { "RLTrainer._checkpoint": { "total": 1.0989468809999607, "count": 4, "is_parallel": true, "self": 1.0989468809999607 } } }, "_update_policy": { "total": 234.4407075409996, "count": 90, "is_parallel": true, "self": 67.43820363199404, "children": { "TorchPPOOptimizer.update": { "total": 167.00250390900555, "count": 4584, "is_parallel": true, "self": 167.00250390900555 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09504834799986384, "count": 1, "self": 0.0014605219998884422, "children": { "RLTrainer._checkpoint": { "total": 0.0935878259999754, "count": 1, "self": 0.0935878259999754 } } } } } } }