{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6742754578590393, "min": 0.6572294235229492, "max": 2.8697307109832764, "count": 37 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6912.671875, "min": 6282.4560546875, "max": 29420.48046875, "count": 37 }, "SnowballTarget.Step.mean": { "value": 369984.0, "min": 9952.0, "max": 369984.0, "count": 37 }, "SnowballTarget.Step.sum": { "value": 369984.0, "min": 9952.0, "max": 369984.0, "count": 37 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.636992454528809, "min": 0.24956205487251282, "max": 13.64618968963623, "count": 37 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2795.58349609375, "min": 48.4150390625, "max": 2795.58349609375, "count": 37 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 37 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 37 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0682096060852785, "min": 0.06041862816326138, "max": 0.07371993287393422, "count": 37 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3410480304263925, "min": 0.25304199170147745, "max": 0.3685996643696711, "count": 37 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17238731743658292, "min": 0.12037395036952825, "max": 0.28751566006856805, "count": 37 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8619365871829145, "min": 0.481495801478113, "max": 1.4375783003428402, "count": 37 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.0002452332182556, "min": 0.0002452332182556, "max": 0.00029918820027059994, "count": 37 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0012261660912779998, "min": 0.0009868728710423998, "max": 0.0014885160038279998, "count": 37 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.18174440000000003, "min": 0.18174440000000003, "max": 0.1997294, "count": 37 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.9087220000000001, "min": 0.7289576, "max": 0.996172, "count": 37 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00408904556, "min": 0.00408904556, "max": 0.004986497059999999, "count": 37 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0204452278, "min": 0.016454984239999998, "max": 0.024808982800000004, "count": 37 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.563636363636363, "min": 3.3636363636363638, "max": 27.21818181818182, "count": 37 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1461.0, "min": 148.0, "max": 1497.0, "count": 37 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.563636363636363, "min": 3.3636363636363638, "max": 27.21818181818182, "count": 37 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1461.0, "min": 148.0, "max": 1497.0, "count": 37 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684841263", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684842429" }, "total": 1166.332405441, "count": 1, "self": 0.30902718700008336, "children": { "run_training.setup": { "total": 0.05011460499997611, "count": 1, "self": 0.05011460499997611 }, "TrainerController.start_learning": { "total": 1165.9732636489998, "count": 1, "self": 1.5252996709873514, "children": { "TrainerController._reset_env": { "total": 4.557932694000101, "count": 1, "self": 4.557932694000101 }, "TrainerController.advance": { "total": 1159.3114185800127, "count": 34177, "self": 0.7695329470179786, "children": { "env_step": { "total": 1158.5418856329948, "count": 34177, "self": 847.3479685240285, "children": { "SubprocessEnvManager._take_step": { "total": 310.4258453029655, "count": 34177, "self": 5.347632055955501, "children": { "TorchPolicy.evaluate": { "total": 305.07821324701, "count": 34177, "self": 305.07821324701 } } }, "workers": { "total": 0.7680718060007621, "count": 34176, "self": 0.0, "children": { "worker_root": { "total": 1161.0795723749839, "count": 34176, "is_parallel": true, "self": 529.0712127690063, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056906660000777265, "count": 1, "is_parallel": true, "self": 0.0040871330003255935, "children": { "_process_rank_one_or_two_observation": { "total": 0.001603532999752133, "count": 10, "is_parallel": true, "self": 0.001603532999752133 } } }, "UnityEnvironment.step": { "total": 0.040440479999915624, "count": 1, "is_parallel": true, "self": 0.0007451939999327806, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003987689999576105, "count": 1, "is_parallel": true, "self": 0.0003987689999576105 }, "communicator.exchange": { "total": 0.03689306100000067, "count": 1, "is_parallel": true, "self": 0.03689306100000067 }, "steps_from_proto": { "total": 0.002403456000024562, "count": 1, "is_parallel": true, "self": 0.00046731999998428364, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019361360000402783, "count": 10, "is_parallel": true, "self": 0.0019361360000402783 } } } } } } }, "UnityEnvironment.step": { "total": 632.0083596059776, "count": 34175, "is_parallel": true, "self": 26.65890390598952, "children": { "UnityEnvironment._generate_step_input": { "total": 13.722595702012313, "count": 34175, "is_parallel": true, "self": 13.722595702012313 }, "communicator.exchange": { "total": 509.04983672796413, "count": 34175, "is_parallel": true, "self": 509.04983672796413 }, "steps_from_proto": { "total": 82.57702327001164, "count": 34175, "is_parallel": true, "self": 17.003406812002822, "children": { "_process_rank_one_or_two_observation": { "total": 65.57361645800881, "count": 341750, "is_parallel": true, "self": 65.57361645800881 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.398999994416954e-05, "count": 1, "self": 6.398999994416954e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1148.5813579310475, "count": 1210253, "is_parallel": true, "self": 29.72853991207603, "children": { "process_trajectory": { "total": 638.4616119709718, "count": 1210253, "is_parallel": true, "self": 635.6798697559717, "children": { "RLTrainer._checkpoint": { "total": 2.781742215000122, "count": 7, "is_parallel": true, "self": 2.781742215000122 } } }, "_update_policy": { "total": 480.3912060479996, "count": 170, "is_parallel": true, "self": 174.43732146799584, "children": { "TorchPPOOptimizer.update": { "total": 305.9538845800038, "count": 8667, "is_parallel": true, "self": 305.9538845800038 } } } } } } } } }, "TrainerController._save_models": { "total": 0.5785487139996803, "count": 1, "self": 0.0026383749996057304, "children": { "RLTrainer._checkpoint": { "total": 0.5759103390000746, "count": 1, "self": 0.5759103390000746 } } } } } } }