{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9427987933158875, "min": 0.9427987933158875, "max": 2.8634934425354004, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9001.8427734375, "min": 9001.8427734375, "max": 29325.03515625, "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": 12.5908203125, "min": 0.32943496108055115, "max": 12.5908203125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2455.2099609375, "min": 63.91038513183594, "max": 2542.163330078125, "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": 0.06561951540981469, "min": 0.06224817634439187, "max": 0.07602773625694681, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26247806163925874, "min": 0.24899270537756749, "max": 0.3586194541410306, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17900981640844954, "min": 0.11869640532634494, "max": 0.2629362608020017, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7160392656337982, "min": 0.47478562130537977, "max": 1.3146813040100087, "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": 24.772727272727273, "min": 3.477272727272727, "max": 25.072727272727274, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1090.0, "min": 153.0, "max": 1379.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.772727272727273, "min": 3.477272727272727, "max": 25.072727272727274, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1090.0, "min": 153.0, "max": 1379.0, "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": "1712832327", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712832794" }, "total": 466.83456040500005, "count": 1, "self": 0.6145600499999659, "children": { "run_training.setup": { "total": 0.05513880300003393, "count": 1, "self": 0.05513880300003393 }, "TrainerController.start_learning": { "total": 466.16486155200005, "count": 1, "self": 0.6069450850005751, "children": { "TrainerController._reset_env": { "total": 2.817758411, "count": 1, "self": 2.817758411 }, "TrainerController.advance": { "total": 462.64469234999945, "count": 18199, "self": 0.29448502999542825, "children": { "env_step": { "total": 462.350207320004, "count": 18199, "self": 300.81623269600027, "children": { "SubprocessEnvManager._take_step": { "total": 161.22573478600066, "count": 18199, "self": 1.5761523310088137, "children": { "TorchPolicy.evaluate": { "total": 159.64958245499184, "count": 18199, "self": 159.64958245499184 } } }, "workers": { "total": 0.3082398380030895, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 464.8801684429967, "count": 18199, "is_parallel": true, "self": 230.67840539999702, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005361335999964467, "count": 1, "is_parallel": true, "self": 0.003796726999951261, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015646090000132062, "count": 10, "is_parallel": true, "self": 0.0015646090000132062 } } }, "UnityEnvironment.step": { "total": 0.04027465800004393, "count": 1, "is_parallel": true, "self": 0.0007213510000383394, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000490806000016164, "count": 1, "is_parallel": true, "self": 0.000490806000016164 }, "communicator.exchange": { "total": 0.03679319999997688, "count": 1, "is_parallel": true, "self": 0.03679319999997688 }, "steps_from_proto": { "total": 0.002269301000012547, "count": 1, "is_parallel": true, "self": 0.00043008200003669117, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018392189999758557, "count": 10, "is_parallel": true, "self": 0.0018392189999758557 } } } } } } }, "UnityEnvironment.step": { "total": 234.2017630429997, "count": 18198, "is_parallel": true, "self": 10.688155428005416, "children": { "UnityEnvironment._generate_step_input": { "total": 5.765126148998718, "count": 18198, "is_parallel": true, "self": 5.765126148998718 }, "communicator.exchange": { "total": 181.27783530799837, "count": 18198, "is_parallel": true, "self": 181.27783530799837 }, "steps_from_proto": { "total": 36.47064615799718, "count": 18198, "is_parallel": true, "self": 6.918889985010196, "children": { "_process_rank_one_or_two_observation": { "total": 29.551756172986984, "count": 181980, "is_parallel": true, "self": 29.551756172986984 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012521799999376526, "count": 1, "self": 0.00012521799999376526, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 456.71403150204605, "count": 700127, "is_parallel": true, "self": 15.182844991956586, "children": { "process_trajectory": { "total": 253.2554293140896, "count": 700127, "is_parallel": true, "self": 252.67248837308966, "children": { "RLTrainer._checkpoint": { "total": 0.5829409409999471, "count": 4, "is_parallel": true, "self": 0.5829409409999471 } } }, "_update_policy": { "total": 188.27575719599986, "count": 90, "is_parallel": true, "self": 54.52593287099978, "children": { "TorchPPOOptimizer.update": { "total": 133.74982432500008, "count": 4587, "is_parallel": true, "self": 133.74982432500008 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09534048800003347, "count": 1, "self": 0.0008928759999662361, "children": { "RLTrainer._checkpoint": { "total": 0.09444761200006724, "count": 1, "self": 0.09444761200006724 } } } } } } }