{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.966218888759613, "min": 0.966218888759613, "max": 2.8785972595214844, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9246.71484375, "min": 9246.71484375, "max": 29669.703125, "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": 13.039606094360352, "min": 0.3568347692489624, "max": 13.039606094360352, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2542.72314453125, "min": 69.22594451904297, "max": 2642.87353515625, "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": 0.06975891135231244, "min": 0.06318818423931268, "max": 0.07469362508324112, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27903564540924974, "min": 0.2527527369572507, "max": 0.37161572841561047, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18729648819448902, "min": 0.11308451788956482, "max": 0.2896522142577405, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7491859527779561, "min": 0.4523380715582593, "max": 1.3924873997183407, "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": 25.454545454545453, "min": 3.227272727272727, "max": 26.145454545454545, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 142.0, "max": 1438.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.227272727272727, "max": 26.145454545454545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 142.0, "max": 1438.0, "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": "1678400968", "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 ./SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678401437" }, "total": 468.419149841, "count": 1, "self": 0.6408715029999144, "children": { "run_training.setup": { "total": 0.10263936600000534, "count": 1, "self": 0.10263936600000534 }, "TrainerController.start_learning": { "total": 467.67563897200006, "count": 1, "self": 0.5705904919944942, "children": { "TrainerController._reset_env": { "total": 8.659449489999986, "count": 1, "self": 8.659449489999986 }, "TrainerController.advance": { "total": 458.23349050500565, "count": 18210, "self": 0.2798876550058935, "children": { "env_step": { "total": 457.95360284999975, "count": 18210, "self": 329.27999608999863, "children": { "SubprocessEnvManager._take_step": { "total": 128.40312378400012, "count": 18210, "self": 2.2169753900006413, "children": { "TorchPolicy.evaluate": { "total": 126.18614839399947, "count": 18210, "self": 126.18614839399947 } } }, "workers": { "total": 0.2704829760010057, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 466.10442206601016, "count": 18210, "is_parallel": true, "self": 224.5745503050132, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028808310000272286, "count": 1, "is_parallel": true, "self": 0.0008153969998261346, "children": { "_process_rank_one_or_two_observation": { "total": 0.002065434000201094, "count": 10, "is_parallel": true, "self": 0.002065434000201094 } } }, "UnityEnvironment.step": { "total": 0.03647131300004958, "count": 1, "is_parallel": true, "self": 0.0004902570001377171, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003175559999704092, "count": 1, "is_parallel": true, "self": 0.0003175559999704092 }, "communicator.exchange": { "total": 0.03384971999997788, "count": 1, "is_parallel": true, "self": 0.03384971999997788 }, "steps_from_proto": { "total": 0.0018137799999635718, "count": 1, "is_parallel": true, "self": 0.00039178899987746263, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014219910000861091, "count": 10, "is_parallel": true, "self": 0.0014219910000861091 } } } } } } }, "UnityEnvironment.step": { "total": 241.52987176099697, "count": 18209, "is_parallel": true, "self": 9.435180765999803, "children": { "UnityEnvironment._generate_step_input": { "total": 5.356918914001426, "count": 18209, "is_parallel": true, "self": 5.356918914001426 }, "communicator.exchange": { "total": 195.08451061799758, "count": 18209, "is_parallel": true, "self": 195.08451061799758 }, "steps_from_proto": { "total": 31.65326146299816, "count": 18209, "is_parallel": true, "self": 6.340710505016091, "children": { "_process_rank_one_or_two_observation": { "total": 25.31255095798207, "count": 182090, "is_parallel": true, "self": 25.31255095798207 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016679399993790867, "count": 1, "self": 0.00016679399993790867, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.4872644729828, "count": 413942, "is_parallel": true, "self": 10.461560591981083, "children": { "process_trajectory": { "total": 252.7423547900015, "count": 413942, "is_parallel": true, "self": 251.69331912800158, "children": { "RLTrainer._checkpoint": { "total": 1.0490356619999375, "count": 4, "is_parallel": true, "self": 1.0490356619999375 } } }, "_update_policy": { "total": 191.28334909100022, "count": 90, "is_parallel": true, "self": 70.69009450499817, "children": { "TorchPPOOptimizer.update": { "total": 120.59325458600205, "count": 4587, "is_parallel": true, "self": 120.59325458600205 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21194169099999272, "count": 1, "self": 0.0011790130000690624, "children": { "RLTrainer._checkpoint": { "total": 0.21076267799992365, "count": 1, "self": 0.21076267799992365 } } } } } } }