{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9668388366699219, "min": 0.9668388366699219, "max": 2.870380163192749, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9242.0126953125, "min": 9242.0126953125, "max": 29395.5625, "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": 12.32931900024414, "min": 0.2696090042591095, "max": 12.32931900024414, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2404.21728515625, "min": 52.30414581298828, "max": 2456.194580078125, "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": 0.06897183521291214, "min": 0.06269468536526854, "max": 0.07825166739742545, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27588734085164857, "min": 0.2607673076700474, "max": 0.39125833698712725, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2310926996390609, "min": 0.12164473905132206, "max": 0.2723868182476829, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9243707985562436, "min": 0.48657895620528824, "max": 1.3619340912384146, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.00029188200270599996, "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": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.045454545454547, "min": 3.227272727272727, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 142.0, "max": 1312.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.227272727272727, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 142.0, "max": 1312.0, "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": "1697190748", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697191240" }, "total": 492.71191789, "count": 1, "self": 0.693102571000054, "children": { "run_training.setup": { "total": 0.08590422099996431, "count": 1, "self": 0.08590422099996431 }, "TrainerController.start_learning": { "total": 491.932911098, "count": 1, "self": 0.7099005360162209, "children": { "TrainerController._reset_env": { "total": 8.057474551000041, "count": 1, "self": 8.057474551000041 }, "TrainerController.advance": { "total": 483.0143870009838, "count": 18206, "self": 0.33149750297889113, "children": { "env_step": { "total": 482.6828894980049, "count": 18206, "self": 325.94831235999436, "children": { "SubprocessEnvManager._take_step": { "total": 156.38368968500527, "count": 18206, "self": 1.6850933049940977, "children": { "TorchPolicy.evaluate": { "total": 154.69859638001117, "count": 18206, "self": 154.69859638001117 } } }, "workers": { "total": 0.3508874530052708, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 490.2191529129784, "count": 18206, "is_parallel": true, "self": 217.31501506896916, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005510815000207003, "count": 1, "is_parallel": true, "self": 0.003877827000223988, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016329879999830155, "count": 10, "is_parallel": true, "self": 0.0016329879999830155 } } }, "UnityEnvironment.step": { "total": 0.0961188989999755, "count": 1, "is_parallel": true, "self": 0.0006932329999926878, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038634399993497937, "count": 1, "is_parallel": true, "self": 0.00038634399993497937 }, "communicator.exchange": { "total": 0.09250984000004792, "count": 1, "is_parallel": true, "self": 0.09250984000004792 }, "steps_from_proto": { "total": 0.0025294819999999163, "count": 1, "is_parallel": true, "self": 0.0004192049998437142, "children": { "_process_rank_one_or_two_observation": { "total": 0.002110277000156202, "count": 10, "is_parallel": true, "self": 0.002110277000156202 } } } } } } }, "UnityEnvironment.step": { "total": 272.90413784400926, "count": 18205, "is_parallel": true, "self": 11.938334625006064, "children": { "UnityEnvironment._generate_step_input": { "total": 6.104260829997884, "count": 18205, "is_parallel": true, "self": 6.104260829997884 }, "communicator.exchange": { "total": 216.21581503498078, "count": 18205, "is_parallel": true, "self": 216.21581503498078 }, "steps_from_proto": { "total": 38.64572735402453, "count": 18205, "is_parallel": true, "self": 7.655899691025979, "children": { "_process_rank_one_or_two_observation": { "total": 30.98982766299855, "count": 182050, "is_parallel": true, "self": 30.98982766299855 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017108199995163886, "count": 1, "self": 0.00017108199995163886, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 478.20302388001073, "count": 555038, "is_parallel": true, "self": 12.448195555924485, "children": { "process_trajectory": { "total": 295.5843077350871, "count": 555038, "is_parallel": true, "self": 294.2834177550874, "children": { "RLTrainer._checkpoint": { "total": 1.300889979999738, "count": 4, "is_parallel": true, "self": 1.300889979999738 } } }, "_update_policy": { "total": 170.17052058899912, "count": 90, "is_parallel": true, "self": 43.534163392004984, "children": { "TorchPPOOptimizer.update": { "total": 126.63635719699414, "count": 3056, "is_parallel": true, "self": 126.63635719699414 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15097792799997478, "count": 1, "self": 0.0011437980001574033, "children": { "RLTrainer._checkpoint": { "total": 0.14983412999981738, "count": 1, "self": 0.14983412999981738 } } } } } } }