{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0156421661376953, "min": 1.0156421661376953, "max": 2.8528153896331787, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9730.8671875, "min": 9730.8671875, "max": 29278.443359375, "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": 12.62112045288086, "min": 0.47841018438339233, "max": 12.62112045288086, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2461.118408203125, "min": 92.81157684326172, "max": 2523.084716796875, "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": 0.06295204235271633, "min": 0.06242026876870488, "max": 0.07422768449118046, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2518081694108653, "min": 0.2518081694108653, "max": 0.36732143348647284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2000907879395812, "min": 0.1388771288649307, "max": 0.29574139460044746, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8003631517583248, "min": 0.5555085154597228, "max": 1.290809950115634, "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": 24.75, "min": 3.7045454545454546, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1089.0, "min": 163.0, "max": 1366.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.75, "min": 3.7045454545454546, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1089.0, "min": 163.0, "max": 1366.0, "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": "1679870176", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679870643" }, "total": 467.36527581700005, "count": 1, "self": 0.738208420000035, "children": { "run_training.setup": { "total": 0.3398252209999839, "count": 1, "self": 0.3398252209999839 }, "TrainerController.start_learning": { "total": 466.28724217600006, "count": 1, "self": 0.5197614180011669, "children": { "TrainerController._reset_env": { "total": 9.82353508700001, "count": 1, "self": 9.82353508700001 }, "TrainerController.advance": { "total": 455.71696450099887, "count": 18215, "self": 0.2686081830009357, "children": { "env_step": { "total": 455.44835631799793, "count": 18215, "self": 326.96080006899535, "children": { "SubprocessEnvManager._take_step": { "total": 128.23118728000307, "count": 18215, "self": 2.256987884006975, "children": { "TorchPolicy.evaluate": { "total": 125.9741993959961, "count": 18215, "self": 125.9741993959961 } } }, "workers": { "total": 0.2563689689994817, "count": 18215, "self": 0.0, "children": { "worker_root": { "total": 464.9127886929948, "count": 18215, "is_parallel": true, "self": 223.05681247699684, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0061613279999903625, "count": 1, "is_parallel": true, "self": 0.003957951000018056, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022033769999723063, "count": 10, "is_parallel": true, "self": 0.0022033769999723063 } } }, "UnityEnvironment.step": { "total": 0.05256154999997875, "count": 1, "is_parallel": true, "self": 0.0006218689999855087, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004362210000010691, "count": 1, "is_parallel": true, "self": 0.0004362210000010691 }, "communicator.exchange": { "total": 0.04955131200000551, "count": 1, "is_parallel": true, "self": 0.04955131200000551 }, "steps_from_proto": { "total": 0.0019521479999866642, "count": 1, "is_parallel": true, "self": 0.0003782659998989857, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015738820000876785, "count": 10, "is_parallel": true, "self": 0.0015738820000876785 } } } } } } }, "UnityEnvironment.step": { "total": 241.85597621599797, "count": 18214, "is_parallel": true, "self": 9.715447058994187, "children": { "UnityEnvironment._generate_step_input": { "total": 5.244629835997273, "count": 18214, "is_parallel": true, "self": 5.244629835997273 }, "communicator.exchange": { "total": 195.95203480200405, "count": 18214, "is_parallel": true, "self": 195.95203480200405 }, "steps_from_proto": { "total": 30.94386451900246, "count": 18214, "is_parallel": true, "self": 6.041323885008637, "children": { "_process_rank_one_or_two_observation": { "total": 24.902540633993823, "count": 182140, "is_parallel": true, "self": 24.902540633993823 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014329700002235768, "count": 1, "self": 0.00014329700002235768, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.1179662250075, "count": 413769, "is_parallel": true, "self": 10.250386030013317, "children": { "process_trajectory": { "total": 254.28806254799426, "count": 413769, "is_parallel": true, "self": 252.7119756909943, "children": { "RLTrainer._checkpoint": { "total": 1.5760868569999502, "count": 4, "is_parallel": true, "self": 1.5760868569999502 } } }, "_update_policy": { "total": 187.5795176469999, "count": 90, "is_parallel": true, "self": 65.74733931899902, "children": { "TorchPPOOptimizer.update": { "total": 121.83217832800088, "count": 4587, "is_parallel": true, "self": 121.83217832800088 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22683787300002223, "count": 1, "self": 0.0012477400000534544, "children": { "RLTrainer._checkpoint": { "total": 0.22559013299996877, "count": 1, "self": 0.22559013299996877 } } } } } } }