{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.995689332485199, "min": 0.9736050367355347, "max": 2.873532772064209, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9506.841796875, "min": 9506.841796875, "max": 29459.45703125, "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": 12.108518600463867, "min": 0.28649312257766724, "max": 12.108518600463867, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2361.1611328125, "min": 55.57966613769531, "max": 2464.79345703125, "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": 0.06378712250507841, "min": 0.06051313130563928, "max": 0.07921260682633147, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25514849002031365, "min": 0.24205252522255713, "max": 0.37709850893759933, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19357738322487067, "min": 0.10876544913523557, "max": 0.2935299242974496, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7743095328994827, "min": 0.4350617965409423, "max": 1.3735135048627853, "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": 23.90909090909091, "min": 3.022727272727273, "max": 24.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1052.0, "min": 133.0, "max": 1325.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.90909090909091, "min": 3.022727272727273, "max": 24.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1052.0, "min": 133.0, "max": 1325.0, "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": "1692554516", "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": "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": "1692554983" }, "total": 466.6911836449999, "count": 1, "self": 0.4306262629995672, "children": { "run_training.setup": { "total": 0.042128094000190686, "count": 1, "self": 0.042128094000190686 }, "TrainerController.start_learning": { "total": 466.21842928800015, "count": 1, "self": 0.5751027149951824, "children": { "TrainerController._reset_env": { "total": 5.074527191000016, "count": 1, "self": 5.074527191000016 }, "TrainerController.advance": { "total": 460.41603867000504, "count": 18202, "self": 0.2656670150172431, "children": { "env_step": { "total": 460.1503716549878, "count": 18202, "self": 334.74594866698635, "children": { "SubprocessEnvManager._take_step": { "total": 125.12491950298727, "count": 18202, "self": 1.8696248689961976, "children": { "TorchPolicy.evaluate": { "total": 123.25529463399107, "count": 18202, "self": 123.25529463399107 } } }, "workers": { "total": 0.27950348501417466, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 464.69151637299, "count": 18202, "is_parallel": true, "self": 217.93803162999984, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005455306000158089, "count": 1, "is_parallel": true, "self": 0.0037676799997825583, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016876260003755306, "count": 10, "is_parallel": true, "self": 0.0016876260003755306 } } }, "UnityEnvironment.step": { "total": 0.08839598499980639, "count": 1, "is_parallel": true, "self": 0.000874630999760484, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040489499997420353, "count": 1, "is_parallel": true, "self": 0.00040489499997420353 }, "communicator.exchange": { "total": 0.07970682600011969, "count": 1, "is_parallel": true, "self": 0.07970682600011969 }, "steps_from_proto": { "total": 0.007409632999952009, "count": 1, "is_parallel": true, "self": 0.0029843249999430554, "children": { "_process_rank_one_or_two_observation": { "total": 0.004425308000008954, "count": 10, "is_parallel": true, "self": 0.004425308000008954 } } } } } } }, "UnityEnvironment.step": { "total": 246.75348474299017, "count": 18201, "is_parallel": true, "self": 10.52973922699266, "children": { "UnityEnvironment._generate_step_input": { "total": 5.204955766994544, "count": 18201, "is_parallel": true, "self": 5.204955766994544 }, "communicator.exchange": { "total": 195.6214024529927, "count": 18201, "is_parallel": true, "self": 195.6214024529927 }, "steps_from_proto": { "total": 35.397387296010265, "count": 18201, "is_parallel": true, "self": 6.3879401649830925, "children": { "_process_rank_one_or_two_observation": { "total": 29.009447131027173, "count": 182010, "is_parallel": true, "self": 29.009447131027173 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001453400000173133, "count": 1, "self": 0.0001453400000173133, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.08547147496324, "count": 435803, "is_parallel": true, "self": 9.031758127055582, "children": { "process_trajectory": { "total": 249.1646005609075, "count": 435803, "is_parallel": true, "self": 248.3552093349076, "children": { "RLTrainer._checkpoint": { "total": 0.8093912259998888, "count": 4, "is_parallel": true, "self": 0.8093912259998888 } } }, "_update_policy": { "total": 198.88911278700016, "count": 90, "is_parallel": true, "self": 80.07020635900949, "children": { "TorchPPOOptimizer.update": { "total": 118.81890642799067, "count": 4587, "is_parallel": true, "self": 118.81890642799067 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15261537199990016, "count": 1, "self": 0.0008528589999059477, "children": { "RLTrainer._checkpoint": { "total": 0.15176251299999421, "count": 1, "self": 0.15176251299999421 } } } } } } }