{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0023980140686035, "min": 1.0023980140686035, "max": 2.847219228744507, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9570.896484375, "min": 9570.896484375, "max": 29221.01171875, "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": 12.78862476348877, "min": 0.3963586390018463, "max": 12.78862476348877, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2493.78173828125, "min": 76.8935775756836, "max": 2573.88623046875, "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": 0.06701212728669406, "min": 0.061001573048427, "max": 0.07422969944880106, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26804850914677625, "min": 0.24996952715731574, "max": 0.3597007110561119, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1826468617016194, "min": 0.11347541279803194, "max": 0.28696800987510124, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7305874468064776, "min": 0.4539016511921278, "max": 1.357964690117275, "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": 25.772727272727273, "min": 3.1136363636363638, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 137.0, "max": 1377.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.1136363636363638, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 137.0, "max": 1377.0, "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": "1680158037", "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": "1680158494" }, "total": 456.909100541, "count": 1, "self": 0.5434781089999774, "children": { "run_training.setup": { "total": 0.1704429330000039, "count": 1, "self": 0.1704429330000039 }, "TrainerController.start_learning": { "total": 456.195179499, "count": 1, "self": 0.5478390350021982, "children": { "TrainerController._reset_env": { "total": 9.115025639999999, "count": 1, "self": 9.115025639999999 }, "TrainerController.advance": { "total": 446.40552081699775, "count": 18202, "self": 0.26863478700477117, "children": { "env_step": { "total": 446.136886029993, "count": 18202, "self": 323.23477105798213, "children": { "SubprocessEnvManager._take_step": { "total": 122.6429601860055, "count": 18202, "self": 2.0445688350015416, "children": { "TorchPolicy.evaluate": { "total": 120.59839135100395, "count": 18202, "self": 120.59839135100395 } } }, "workers": { "total": 0.2591547860053538, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 454.87479290900444, "count": 18202, "is_parallel": true, "self": 218.28133869100782, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006714703999989524, "count": 1, "is_parallel": true, "self": 0.004362740000033227, "children": { "_process_rank_one_or_two_observation": { "total": 0.002351963999956297, "count": 10, "is_parallel": true, "self": 0.002351963999956297 } } }, "UnityEnvironment.step": { "total": 0.033933636999961436, "count": 1, "is_parallel": true, "self": 0.0005460269999275624, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003014929999949345, "count": 1, "is_parallel": true, "self": 0.0003014929999949345 }, "communicator.exchange": { "total": 0.03129028900002595, "count": 1, "is_parallel": true, "self": 0.03129028900002595 }, "steps_from_proto": { "total": 0.001795828000012989, "count": 1, "is_parallel": true, "self": 0.000376266000216674, "children": { "_process_rank_one_or_two_observation": { "total": 0.001419561999796315, "count": 10, "is_parallel": true, "self": 0.001419561999796315 } } } } } } }, "UnityEnvironment.step": { "total": 236.59345421799662, "count": 18201, "is_parallel": true, "self": 9.38550327101575, "children": { "UnityEnvironment._generate_step_input": { "total": 5.055818991997512, "count": 18201, "is_parallel": true, "self": 5.055818991997512 }, "communicator.exchange": { "total": 192.16952546198706, "count": 18201, "is_parallel": true, "self": 192.16952546198706 }, "steps_from_proto": { "total": 29.982606492996297, "count": 18201, "is_parallel": true, "self": 5.886100144995055, "children": { "_process_rank_one_or_two_observation": { "total": 24.096506348001242, "count": 182010, "is_parallel": true, "self": 24.096506348001242 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001477040000281704, "count": 1, "self": 0.0001477040000281704, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 443.10730041502705, "count": 391355, "is_parallel": true, "self": 9.50435259898228, "children": { "process_trajectory": { "total": 245.9425565180448, "count": 391355, "is_parallel": true, "self": 244.25885134404484, "children": { "RLTrainer._checkpoint": { "total": 1.6837051739999538, "count": 4, "is_parallel": true, "self": 1.6837051739999538 } } }, "_update_policy": { "total": 187.66039129799998, "count": 90, "is_parallel": true, "self": 70.15239388199848, "children": { "TorchPPOOptimizer.update": { "total": 117.5079974160015, "count": 4584, "is_parallel": true, "self": 117.5079974160015 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12664630300002955, "count": 1, "self": 0.0008546349999960512, "children": { "RLTrainer._checkpoint": { "total": 0.1257916680000335, "count": 1, "self": 0.1257916680000335 } } } } } } }