{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9872555732727051, "min": 0.9872555732727051, "max": 2.8651630878448486, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9426.31640625, "min": 9426.31640625, "max": 29373.65234375, "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": 11.663482666015625, "min": 0.4524121880531311, "max": 11.663482666015625, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2274.379150390625, "min": 87.7679672241211, "max": 2365.9462890625, "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": 0.06776706428439973, "min": 0.06343220545900027, "max": 0.07438325787889861, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2710682571375989, "min": 0.2537288218360011, "max": 0.37191628939449306, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20560861528650218, "min": 0.16335063743834183, "max": 0.29535982056575666, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8224344611460087, "min": 0.6534025497533673, "max": 1.4549375591324827, "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": 23.272727272727273, "min": 4.2272727272727275, "max": 23.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1024.0, "min": 186.0, "max": 1270.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.272727272727273, "min": 4.2272727272727275, "max": 23.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1024.0, "min": 186.0, "max": 1270.0, "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": "1701258372", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701258867" }, "total": 495.22908049600005, "count": 1, "self": 0.39543255499995666, "children": { "run_training.setup": { "total": 0.08722484600002645, "count": 1, "self": 0.08722484600002645 }, "TrainerController.start_learning": { "total": 494.74642309500007, "count": 1, "self": 0.5786796929756974, "children": { "TrainerController._reset_env": { "total": 3.5699816990000954, "count": 1, "self": 3.5699816990000954 }, "TrainerController.advance": { "total": 490.50950844702413, "count": 18200, "self": 0.2837790660189512, "children": { "env_step": { "total": 490.2257293810052, "count": 18200, "self": 331.5158235749957, "children": { "SubprocessEnvManager._take_step": { "total": 158.26325622301363, "count": 18200, "self": 1.5401593430162848, "children": { "TorchPolicy.evaluate": { "total": 156.72309687999734, "count": 18200, "self": 156.72309687999734 } } }, "workers": { "total": 0.44664958299586033, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 493.50698254002305, "count": 18200, "is_parallel": true, "self": 242.95517119902195, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0055383119999987684, "count": 1, "is_parallel": true, "self": 0.0040055419998452635, "children": { "_process_rank_one_or_two_observation": { "total": 0.001532770000153505, "count": 10, "is_parallel": true, "self": 0.001532770000153505 } } }, "UnityEnvironment.step": { "total": 0.05208088599999883, "count": 1, "is_parallel": true, "self": 0.0007073119999176924, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004311710000592939, "count": 1, "is_parallel": true, "self": 0.0004311710000592939 }, "communicator.exchange": { "total": 0.04860716799998954, "count": 1, "is_parallel": true, "self": 0.04860716799998954 }, "steps_from_proto": { "total": 0.0023352350000322986, "count": 1, "is_parallel": true, "self": 0.000581627000201479, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017536079998308196, "count": 10, "is_parallel": true, "self": 0.0017536079998308196 } } } } } } }, "UnityEnvironment.step": { "total": 250.5518113410011, "count": 18199, "is_parallel": true, "self": 11.088266580996105, "children": { "UnityEnvironment._generate_step_input": { "total": 5.7517716289991085, "count": 18199, "is_parallel": true, "self": 5.7517716289991085 }, "communicator.exchange": { "total": 197.54487712798777, "count": 18199, "is_parallel": true, "self": 197.54487712798777 }, "steps_from_proto": { "total": 36.16689600301811, "count": 18199, "is_parallel": true, "self": 6.718520838998643, "children": { "_process_rank_one_or_two_observation": { "total": 29.448375164019467, "count": 181990, "is_parallel": true, "self": 29.448375164019467 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.682300004787976e-05, "count": 1, "self": 4.682300004787976e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 486.1088444819386, "count": 519988, "is_parallel": true, "self": 11.535920828868484, "children": { "process_trajectory": { "total": 276.6040145200707, "count": 519988, "is_parallel": true, "self": 275.5732867900707, "children": { "RLTrainer._checkpoint": { "total": 1.0307277299999669, "count": 4, "is_parallel": true, "self": 1.0307277299999669 } } }, "_update_policy": { "total": 197.96890913299944, "count": 90, "is_parallel": true, "self": 61.632394078998345, "children": { "TorchPPOOptimizer.update": { "total": 136.3365150540011, "count": 4587, "is_parallel": true, "self": 136.3365150540011 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08820643300009579, "count": 1, "self": 0.0008407000000261178, "children": { "RLTrainer._checkpoint": { "total": 0.08736573300006967, "count": 1, "self": 0.08736573300006967 } } } } } } }