{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0554320812225342, "min": 1.0483535528182983, "max": 2.876040458679199, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10100.4853515625, "min": 10100.4853515625, "max": 29485.16796875, "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": 12.838669776916504, "min": 0.3388391137123108, "max": 12.838669776916504, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2503.54052734375, "min": 65.73478698730469, "max": 2614.40625, "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": 0.06534117087422227, "min": 0.06073270956737057, "max": 0.07159282308973215, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26136468349688907, "min": 0.24293083826948228, "max": 0.35687205634723584, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2103917467243531, "min": 0.11479117890806212, "max": 0.30243143854187987, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8415669868974124, "min": 0.4591647156322485, "max": 1.5121571927093993, "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": 25.363636363636363, "min": 2.9318181818181817, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 129.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 2.9318181818181817, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 129.0, "max": 1374.0, "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": "1690265015", "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": "1690265491" }, "total": 476.63112868100006, "count": 1, "self": 0.4377098070000329, "children": { "run_training.setup": { "total": 0.035099466999952256, "count": 1, "self": 0.035099466999952256 }, "TrainerController.start_learning": { "total": 476.1583194070001, "count": 1, "self": 0.5897973579989753, "children": { "TrainerController._reset_env": { "total": 5.1314352429999985, "count": 1, "self": 5.1314352429999985 }, "TrainerController.advance": { "total": 470.2987419720012, "count": 18203, "self": 0.27803992799505295, "children": { "env_step": { "total": 470.02070204400616, "count": 18203, "self": 341.9424563339987, "children": { "SubprocessEnvManager._take_step": { "total": 127.79112912900462, "count": 18203, "self": 1.8496102219962722, "children": { "TorchPolicy.evaluate": { "total": 125.94151890700834, "count": 18203, "self": 125.94151890700834 } } }, "workers": { "total": 0.28711658100286286, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 474.40423071700394, "count": 18203, "is_parallel": true, "self": 225.832465315006, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0055090690000270115, "count": 1, "is_parallel": true, "self": 0.004036763999977211, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014723050000498006, "count": 10, "is_parallel": true, "self": 0.0014723050000498006 } } }, "UnityEnvironment.step": { "total": 0.03537119600002825, "count": 1, "is_parallel": true, "self": 0.0005973190000077011, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028001900000163005, "count": 1, "is_parallel": true, "self": 0.00028001900000163005 }, "communicator.exchange": { "total": 0.03239055900002086, "count": 1, "is_parallel": true, "self": 0.03239055900002086 }, "steps_from_proto": { "total": 0.00210329899999806, "count": 1, "is_parallel": true, "self": 0.0005553500000132772, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015479489999847829, "count": 10, "is_parallel": true, "self": 0.0015479489999847829 } } } } } } }, "UnityEnvironment.step": { "total": 248.57176540199794, "count": 18202, "is_parallel": true, "self": 10.406791557979204, "children": { "UnityEnvironment._generate_step_input": { "total": 5.227959847010936, "count": 18202, "is_parallel": true, "self": 5.227959847010936 }, "communicator.exchange": { "total": 197.78867576000783, "count": 18202, "is_parallel": true, "self": 197.78867576000783 }, "steps_from_proto": { "total": 35.14833823699996, "count": 18202, "is_parallel": true, "self": 6.597424476990966, "children": { "_process_rank_one_or_two_observation": { "total": 28.550913760008996, "count": 182020, "is_parallel": true, "self": 28.550913760008996 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015786299991304986, "count": 1, "self": 0.00015786299991304986, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 466.4606335659907, "count": 435995, "is_parallel": true, "self": 9.926522858977307, "children": { "process_trajectory": { "total": 255.3559902270133, "count": 435995, "is_parallel": true, "self": 254.12001368301333, "children": { "RLTrainer._checkpoint": { "total": 1.235976543999982, "count": 4, "is_parallel": true, "self": 1.235976543999982 } } }, "_update_policy": { "total": 201.17812048000008, "count": 90, "is_parallel": true, "self": 79.20008518299528, "children": { "TorchPPOOptimizer.update": { "total": 121.9780352970048, "count": 4587, "is_parallel": true, "self": 121.9780352970048 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1381869709999819, "count": 1, "self": 0.000834948999909102, "children": { "RLTrainer._checkpoint": { "total": 0.1373520220000728, "count": 1, "self": 0.1373520220000728 } } } } } } }