{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8710492849349976, "min": 0.8518194556236267, "max": 2.8703958988189697, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8345.5234375, "min": 8345.5234375, "max": 29490.447265625, "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": 12.79319953918457, "min": 0.2925075590610504, "max": 12.79319953918457, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2494.673828125, "min": 56.74646759033203, "max": 2592.645751953125, "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": 0.06976113303864943, "min": 0.0632863223521888, "max": 0.07240389248324267, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27904453215459774, "min": 0.2600812221484661, "max": 0.36201946241621336, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19811935649783005, "min": 0.10474092168642171, "max": 0.2668339875252808, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7924774259913202, "min": 0.41896368674568685, "max": 1.3246205034209233, "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": 25.295454545454547, "min": 3.1818181818181817, "max": 25.327272727272728, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 140.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.1818181818181817, "max": 25.327272727272728, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 140.0, "max": 1393.0, "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": "1681936241", "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": "1681936725" }, "total": 483.9162142839999, "count": 1, "self": 0.388402205000034, "children": { "run_training.setup": { "total": 0.11233140599995295, "count": 1, "self": 0.11233140599995295 }, "TrainerController.start_learning": { "total": 483.41548067299993, "count": 1, "self": 0.6049490640074282, "children": { "TrainerController._reset_env": { "total": 3.9011338939999405, "count": 1, "self": 3.9011338939999405 }, "TrainerController.advance": { "total": 478.77667707899263, "count": 18203, "self": 0.3099641750052342, "children": { "env_step": { "total": 478.4667129039874, "count": 18203, "self": 351.86008752201724, "children": { "SubprocessEnvManager._take_step": { "total": 126.29959967897696, "count": 18203, "self": 1.869588875985528, "children": { "TorchPolicy.evaluate": { "total": 124.43001080299143, "count": 18203, "self": 124.43001080299143 } } }, "workers": { "total": 0.30702570299320087, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 481.7772536189884, "count": 18203, "is_parallel": true, "self": 220.00104604000103, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004736011000090912, "count": 1, "is_parallel": true, "self": 0.003257434999909492, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014785760001814197, "count": 10, "is_parallel": true, "self": 0.0014785760001814197 } } }, "UnityEnvironment.step": { "total": 0.034925987000065106, "count": 1, "is_parallel": true, "self": 0.0005744150000737136, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031744299997171765, "count": 1, "is_parallel": true, "self": 0.00031744299997171765 }, "communicator.exchange": { "total": 0.032217339999988326, "count": 1, "is_parallel": true, "self": 0.032217339999988326 }, "steps_from_proto": { "total": 0.0018167890000313491, "count": 1, "is_parallel": true, "self": 0.00038943899994592357, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014273500000854256, "count": 10, "is_parallel": true, "self": 0.0014273500000854256 } } } } } } }, "UnityEnvironment.step": { "total": 261.7762075789874, "count": 18202, "is_parallel": true, "self": 10.563528492943078, "children": { "UnityEnvironment._generate_step_input": { "total": 5.62348255601637, "count": 18202, "is_parallel": true, "self": 5.62348255601637 }, "communicator.exchange": { "total": 212.58259772501742, "count": 18202, "is_parallel": true, "self": 212.58259772501742 }, "steps_from_proto": { "total": 33.006598805010526, "count": 18202, "is_parallel": true, "self": 6.625489536039822, "children": { "_process_rank_one_or_two_observation": { "total": 26.381109268970704, "count": 182020, "is_parallel": true, "self": 26.381109268970704 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011029200004486484, "count": 1, "self": 0.00011029200004486484, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 475.0363472409464, "count": 435216, "is_parallel": true, "self": 10.776500604923285, "children": { "process_trajectory": { "total": 264.4842430530224, "count": 435216, "is_parallel": true, "self": 263.0290652100224, "children": { "RLTrainer._checkpoint": { "total": 1.4551778430000013, "count": 4, "is_parallel": true, "self": 1.4551778430000013 } } }, "_update_policy": { "total": 199.7756035830007, "count": 90, "is_parallel": true, "self": 72.47733421200519, "children": { "TorchPPOOptimizer.update": { "total": 127.29826937099551, "count": 4587, "is_parallel": true, "self": 127.29826937099551 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13261034399988603, "count": 1, "self": 0.0008453190000636823, "children": { "RLTrainer._checkpoint": { "total": 0.13176502499982234, "count": 1, "self": 0.13176502499982234 } } } } } } }