{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0732603073120117, "min": 1.0732603073120117, "max": 2.8673605918884277, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10282.9072265625, "min": 10282.9072265625, "max": 29333.09765625, "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": 11.764761924743652, "min": 0.22299404442310333, "max": 11.764761924743652, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2294.128662109375, "min": 43.26084518432617, "max": 2366.134765625, "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": 0.06701173867166325, "min": 0.06435791394261267, "max": 0.07276825311351322, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.268046954686653, "min": 0.2594403299604606, "max": 0.3516860720707222, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2031152889716859, "min": 0.12648915066885963, "max": 0.27281542855653756, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8124611558867436, "min": 0.5059566026754385, "max": 1.3467586931644702, "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": 23.477272727272727, "min": 2.9545454545454546, "max": 23.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1033.0, "min": 130.0, "max": 1272.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.477272727272727, "min": 2.9545454545454546, "max": 23.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1033.0, "min": 130.0, "max": 1272.0, "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": "1690667749", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690668225" }, "total": 476.10949766300007, "count": 1, "self": 0.43540280300004497, "children": { "run_training.setup": { "total": 0.03617967200000294, "count": 1, "self": 0.03617967200000294 }, "TrainerController.start_learning": { "total": 475.637915188, "count": 1, "self": 0.5561777380112289, "children": { "TrainerController._reset_env": { "total": 6.724936955000032, "count": 1, "self": 6.724936955000032 }, "TrainerController.advance": { "total": 468.2075254389887, "count": 18204, "self": 0.2701097929851244, "children": { "env_step": { "total": 467.93741564600356, "count": 18204, "self": 338.216636814997, "children": { "SubprocessEnvManager._take_step": { "total": 129.44077087800355, "count": 18204, "self": 1.893805489998897, "children": { "TorchPolicy.evaluate": { "total": 127.54696538800465, "count": 18204, "self": 127.54696538800465 } } }, "workers": { "total": 0.2800079530030075, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 474.09771140800126, "count": 18204, "is_parallel": true, "self": 226.42490357900755, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006307617000004484, "count": 1, "is_parallel": true, "self": 0.00469923399992922, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016083830000752641, "count": 10, "is_parallel": true, "self": 0.0016083830000752641 } } }, "UnityEnvironment.step": { "total": 0.0939640390000136, "count": 1, "is_parallel": true, "self": 0.0006714200000033088, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004210259999695154, "count": 1, "is_parallel": true, "self": 0.0004210259999695154 }, "communicator.exchange": { "total": 0.09063362300003064, "count": 1, "is_parallel": true, "self": 0.09063362300003064 }, "steps_from_proto": { "total": 0.0022379700000101366, "count": 1, "is_parallel": true, "self": 0.000441203000036694, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017967669999734426, "count": 10, "is_parallel": true, "self": 0.0017967669999734426 } } } } } } }, "UnityEnvironment.step": { "total": 247.6728078289937, "count": 18203, "is_parallel": true, "self": 10.727878885009147, "children": { "UnityEnvironment._generate_step_input": { "total": 5.234757822000233, "count": 18203, "is_parallel": true, "self": 5.234757822000233 }, "communicator.exchange": { "total": 196.19607679499478, "count": 18203, "is_parallel": true, "self": 196.19607679499478 }, "steps_from_proto": { "total": 35.51409432698955, "count": 18203, "is_parallel": true, "self": 6.539636991985503, "children": { "_process_rank_one_or_two_observation": { "total": 28.974457335004047, "count": 182030, "is_parallel": true, "self": 28.974457335004047 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015610299999480048, "count": 1, "self": 0.00015610299999480048, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 464.532719039993, "count": 431243, "is_parallel": true, "self": 10.164241009993248, "children": { "process_trajectory": { "total": 255.22730520300036, "count": 431243, "is_parallel": true, "self": 253.9664912430004, "children": { "RLTrainer._checkpoint": { "total": 1.2608139599999504, "count": 4, "is_parallel": true, "self": 1.2608139599999504 } } }, "_update_policy": { "total": 199.14117282699942, "count": 90, "is_parallel": true, "self": 75.8056922760012, "children": { "TorchPPOOptimizer.update": { "total": 123.33548055099823, "count": 4587, "is_parallel": true, "self": 123.33548055099823 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14911895300008382, "count": 1, "self": 0.0009068960001741289, "children": { "RLTrainer._checkpoint": { "total": 0.1482120569999097, "count": 1, "self": 0.1482120569999097 } } } } } } }