{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9101918339729309, "min": 0.9101918339729309, "max": 2.878467082977295, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8710.5361328125, "min": 8710.5361328125, "max": 29541.70703125, "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": 12.863256454467773, "min": 0.27872857451438904, "max": 12.863256454467773, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2508.3349609375, "min": 54.07334518432617, "max": 2569.6796875, "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": 0.0657368723549994, "min": 0.062348225334740257, "max": 0.07524307606001066, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2629474894199976, "min": 0.24939290133896103, "max": 0.37621538030005325, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1929372784992059, "min": 0.12975950171376635, "max": 0.2745354071551678, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7717491139968236, "min": 0.5190380068550654, "max": 1.3726770357758389, "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": 25.568181818181817, "min": 3.522727272727273, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 155.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 3.522727272727273, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 155.0, "max": 1394.0, "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": "1702161606", "python_version": "3.10.11 (main, Apr 20 2023, 19:02:41) [GCC 11.2.0]", "command_line_arguments": "/home/lab_rat/.local/bin/mlagents-learn /app/data/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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702161947" }, "total": 341.1833026280001, "count": 1, "self": 0.3215693639995152, "children": { "run_training.setup": { "total": 0.03329249800026446, "count": 1, "self": 0.03329249800026446 }, "TrainerController.start_learning": { "total": 340.8284407660003, "count": 1, "self": 0.4098355629530488, "children": { "TrainerController._reset_env": { "total": 3.633220007000091, "count": 1, "self": 3.633220007000091 }, "TrainerController.advance": { "total": 336.7166611400471, "count": 18201, "self": 0.20367436298965913, "children": { "env_step": { "total": 336.51298677705745, "count": 18201, "self": 221.7901867890123, "children": { "SubprocessEnvManager._take_step": { "total": 114.49828098403214, "count": 18201, "self": 0.9422720530283186, "children": { "TorchPolicy.evaluate": { "total": 113.55600893100382, "count": 18201, "self": 113.55600893100382 } } }, "workers": { "total": 0.22451900401301828, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 340.134361257974, "count": 18201, "is_parallel": true, "self": 177.6674857129583, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.015762795999762602, "count": 1, "is_parallel": true, "self": 0.01453125000170985, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012315459980527521, "count": 10, "is_parallel": true, "self": 0.0012315459980527521 } } }, "UnityEnvironment.step": { "total": 0.03421265599990875, "count": 1, "is_parallel": true, "self": 0.00038011899869161425, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002405540008112439, "count": 1, "is_parallel": true, "self": 0.0002405540008112439 }, "communicator.exchange": { "total": 0.03230222700040031, "count": 1, "is_parallel": true, "self": 0.03230222700040031 }, "steps_from_proto": { "total": 0.0012897560000055819, "count": 1, "is_parallel": true, "self": 0.0002719859985518269, "children": { "_process_rank_one_or_two_observation": { "total": 0.001017770001453755, "count": 10, "is_parallel": true, "self": 0.001017770001453755 } } } } } } }, "UnityEnvironment.step": { "total": 162.46687554501568, "count": 18200, "is_parallel": true, "self": 8.07504978594443, "children": { "UnityEnvironment._generate_step_input": { "total": 4.106606427046245, "count": 18200, "is_parallel": true, "self": 4.106606427046245 }, "communicator.exchange": { "total": 126.61436451299687, "count": 18200, "is_parallel": true, "self": 126.61436451299687 }, "steps_from_proto": { "total": 23.670854819028136, "count": 18200, "is_parallel": true, "self": 4.536883388311253, "children": { "_process_rank_one_or_two_observation": { "total": 19.133971430716883, "count": 182000, "is_parallel": true, "self": 19.133971430716883 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010768300035124412, "count": 1, "self": 0.00010768300035124412, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 335.6605489069234, "count": 228113, "is_parallel": true, "self": 3.4522701090036207, "children": { "process_trajectory": { "total": 185.9100109679157, "count": 228113, "is_parallel": true, "self": 185.52683832991625, "children": { "RLTrainer._checkpoint": { "total": 0.38317263799945067, "count": 4, "is_parallel": true, "self": 0.38317263799945067 } } }, "_update_policy": { "total": 146.29826783000408, "count": 90, "is_parallel": true, "self": 36.755152765989806, "children": { "TorchPPOOptimizer.update": { "total": 109.54311506401427, "count": 4587, "is_parallel": true, "self": 109.54311506401427 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06861637299971335, "count": 1, "self": 0.00043250899943814147, "children": { "RLTrainer._checkpoint": { "total": 0.06818386400027521, "count": 1, "self": 0.06818386400027521 } } } } } } }