{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0021921396255493, "min": 1.0021921396255493, "max": 2.856139898300171, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9602.0029296875, "min": 9602.0029296875, "max": 29312.564453125, "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": 13.36907958984375, "min": 0.3789811134338379, "max": 13.36907958984375, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2606.970458984375, "min": 73.5223388671875, "max": 2710.776611328125, "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": 0.060274857009633205, "min": 0.060274857009633205, "max": 0.07401087750636803, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24109942803853282, "min": 0.24109942803853282, "max": 0.36115960359593907, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18278574370139952, "min": 0.1325587125417466, "max": 0.2685516300154667, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7311429748055981, "min": 0.5302348501669863, "max": 1.3427581500773336, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.6940097306000015e-05, "min": 2.6940097306000015e-05, "max": 0.000972940002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00010776038922400006, "min": 0.00010776038922400006, "max": 0.004617200038280001, "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": 26.363636363636363, "min": 3.6818181818181817, "max": 26.381818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1160.0, "min": 162.0, "max": 1451.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.363636363636363, "min": 3.6818181818181817, "max": 26.381818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1160.0, "min": 162.0, "max": 1451.0, "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": "1681978052", "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": "1681978659" }, "total": 607.1494858819999, "count": 1, "self": 0.5448061489998963, "children": { "run_training.setup": { "total": 0.14229666700009602, "count": 1, "self": 0.14229666700009602 }, "TrainerController.start_learning": { "total": 606.4623830659999, "count": 1, "self": 0.8669223429874364, "children": { "TrainerController._reset_env": { "total": 1.1251950289999968, "count": 1, "self": 1.1251950289999968 }, "TrainerController.advance": { "total": 604.3065561400125, "count": 18219, "self": 0.4727914920171088, "children": { "env_step": { "total": 603.8337646479954, "count": 18219, "self": 488.5744498209966, "children": { "SubprocessEnvManager._take_step": { "total": 114.74360645099637, "count": 18219, "self": 3.1584199729886677, "children": { "TorchPolicy.evaluate": { "total": 111.5851864780077, "count": 18219, "self": 111.5851864780077 } } }, "workers": { "total": 0.5157083760024079, "count": 18219, "self": 0.0, "children": { "worker_root": { "total": 604.0579600969976, "count": 18219, "is_parallel": true, "self": 264.0842073920031, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0080187080000087, "count": 1, "is_parallel": true, "self": 0.005666873999985, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023518340000237004, "count": 10, "is_parallel": true, "self": 0.0023518340000237004 } } }, "UnityEnvironment.step": { "total": 0.048483002000011766, "count": 1, "is_parallel": true, "self": 0.0008277580001276874, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005408470000247689, "count": 1, "is_parallel": true, "self": 0.0005408470000247689 }, "communicator.exchange": { "total": 0.04395661999990352, "count": 1, "is_parallel": true, "self": 0.04395661999990352 }, "steps_from_proto": { "total": 0.003157776999955786, "count": 1, "is_parallel": true, "self": 0.0008198619998438517, "children": { "_process_rank_one_or_two_observation": { "total": 0.002337915000111934, "count": 10, "is_parallel": true, "self": 0.002337915000111934 } } } } } } }, "UnityEnvironment.step": { "total": 339.97375270499447, "count": 18218, "is_parallel": true, "self": 14.468753163994506, "children": { "UnityEnvironment._generate_step_input": { "total": 7.707607290987539, "count": 18218, "is_parallel": true, "self": 7.707607290987539 }, "communicator.exchange": { "total": 272.3970119050108, "count": 18218, "is_parallel": true, "self": 272.3970119050108 }, "steps_from_proto": { "total": 45.40038034500162, "count": 18218, "is_parallel": true, "self": 9.438870183973336, "children": { "_process_rank_one_or_two_observation": { "total": 35.961510161028286, "count": 182180, "is_parallel": true, "self": 35.961510161028286 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002293659999850206, "count": 1, "self": 0.0002293659999850206, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 598.5402126321495, "count": 604501, "is_parallel": true, "self": 16.539424808215927, "children": { "process_trajectory": { "total": 323.93127487193306, "count": 604501, "is_parallel": true, "self": 322.2869383229331, "children": { "RLTrainer._checkpoint": { "total": 1.644336548999945, "count": 4, "is_parallel": true, "self": 1.644336548999945 } } }, "_update_policy": { "total": 258.06951295200054, "count": 90, "is_parallel": true, "self": 87.3400163740099, "children": { "TorchPPOOptimizer.update": { "total": 170.72949657799063, "count": 4587, "is_parallel": true, "self": 170.72949657799063 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1634801879999941, "count": 1, "self": 0.0015275700000074721, "children": { "RLTrainer._checkpoint": { "total": 0.16195261799998661, "count": 1, "self": 0.16195261799998661 } } } } } } }