{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1593732833862305, "min": 1.1593732833862305, "max": 2.8774361610412598, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11120.708984375, "min": 11120.708984375, "max": 29467.82421875, "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": 12.741241455078125, "min": 0.2262105494737625, "max": 12.741241455078125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2484.5419921875, "min": 43.88484573364258, "max": 2570.5, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06741159189985803, "min": 0.06339085887747761, "max": 0.07670398668885943, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2696463675994321, "min": 0.26904223460188204, "max": 0.3639720135057966, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1890676492715583, "min": 0.11796978490162349, "max": 0.2717500839163275, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7562705970862332, "min": 0.47187913960649397, "max": 1.3587504195816376, "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": 25.431818181818183, "min": 3.1363636363636362, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 138.0, "max": 1369.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.1363636363636362, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 138.0, "max": 1369.0, "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": "1688247332", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688247781" }, "total": 449.04056955500005, "count": 1, "self": 0.434044933999985, "children": { "run_training.setup": { "total": 0.04041791999998168, "count": 1, "self": 0.04041791999998168 }, "TrainerController.start_learning": { "total": 448.5661067010001, "count": 1, "self": 0.49305388799768934, "children": { "TrainerController._reset_env": { "total": 4.119759347000013, "count": 1, "self": 4.119759347000013 }, "TrainerController.advance": { "total": 443.8188796610025, "count": 18205, "self": 0.25227003001043613, "children": { "env_step": { "total": 443.56660963099205, "count": 18205, "self": 322.5336412209823, "children": { "SubprocessEnvManager._take_step": { "total": 120.78486944501299, "count": 18205, "self": 1.6962796190189238, "children": { "TorchPolicy.evaluate": { "total": 119.08858982599406, "count": 18205, "self": 119.08858982599406 } } }, "workers": { "total": 0.24809896499675688, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 447.19307397400075, "count": 18205, "is_parallel": true, "self": 210.40876136599604, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056666980000272815, "count": 1, "is_parallel": true, "self": 0.00411737199988238, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015493260001449016, "count": 10, "is_parallel": true, "self": 0.0015493260001449016 } } }, "UnityEnvironment.step": { "total": 0.07438877499998853, "count": 1, "is_parallel": true, "self": 0.0006357310001021688, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004237040000134584, "count": 1, "is_parallel": true, "self": 0.0004237040000134584 }, "communicator.exchange": { "total": 0.06991729199990004, "count": 1, "is_parallel": true, "self": 0.06991729199990004 }, "steps_from_proto": { "total": 0.003412047999972856, "count": 1, "is_parallel": true, "self": 0.0016736249997393315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017384230002335244, "count": 10, "is_parallel": true, "self": 0.0017384230002335244 } } } } } } }, "UnityEnvironment.step": { "total": 236.7843126080047, "count": 18204, "is_parallel": true, "self": 10.114378105017295, "children": { "UnityEnvironment._generate_step_input": { "total": 5.0740133769833164, "count": 18204, "is_parallel": true, "self": 5.0740133769833164 }, "communicator.exchange": { "total": 188.16846498100722, "count": 18204, "is_parallel": true, "self": 188.16846498100722 }, "steps_from_proto": { "total": 33.42745614499688, "count": 18204, "is_parallel": true, "self": 6.082908632023305, "children": { "_process_rank_one_or_two_observation": { "total": 27.344547512973577, "count": 182040, "is_parallel": true, "self": 27.344547512973577 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011037800004487508, "count": 1, "self": 0.00011037800004487508, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 440.31917174400394, "count": 417072, "is_parallel": true, "self": 9.34446116202946, "children": { "process_trajectory": { "total": 241.41156855397446, "count": 417072, "is_parallel": true, "self": 240.67355991597447, "children": { "RLTrainer._checkpoint": { "total": 0.7380086379999966, "count": 4, "is_parallel": true, "self": 0.7380086379999966 } } }, "_update_policy": { "total": 189.56314202800002, "count": 90, "is_parallel": true, "self": 71.7876880179989, "children": { "TorchPPOOptimizer.update": { "total": 117.77545401000111, "count": 4587, "is_parallel": true, "self": 117.77545401000111 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13430342699984976, "count": 1, "self": 0.0010017069998866646, "children": { "RLTrainer._checkpoint": { "total": 0.1333017199999631, "count": 1, "self": 0.1333017199999631 } } } } } } }