{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0864362716674805, "min": 1.0864362716674805, "max": 2.866999626159668, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10397.1953125, "min": 10397.1953125, "max": 29424.017578125, "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": 12.723920822143555, "min": 0.438618540763855, "max": 12.723920822143555, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2481.16455078125, "min": 85.09199523925781, "max": 2586.970703125, "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": 0.07398353388855991, "min": 0.062391325612278545, "max": 0.07556670641728595, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29593413555423964, "min": 0.24956530244911418, "max": 0.3778335320864298, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19874395912184434, "min": 0.1349035659622328, "max": 0.2907860150524214, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7949758364873774, "min": 0.5396142638489312, "max": 1.3649491931257003, "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": 3.8863636363636362, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 171.0, "max": 1356.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.8863636363636362, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 171.0, "max": 1356.0, "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": "1679513469", "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": "1679513966" }, "total": 497.17111775399985, "count": 1, "self": 0.4348762159997932, "children": { "run_training.setup": { "total": 0.10690313300005982, "count": 1, "self": 0.10690313300005982 }, "TrainerController.start_learning": { "total": 496.629338405, "count": 1, "self": 0.6440272659890525, "children": { "TrainerController._reset_env": { "total": 8.607757148000019, "count": 1, "self": 8.607757148000019 }, "TrainerController.advance": { "total": 487.2412027480109, "count": 18203, "self": 0.33356521601490385, "children": { "env_step": { "total": 486.907637531996, "count": 18203, "self": 353.5404339320007, "children": { "SubprocessEnvManager._take_step": { "total": 133.04667122400144, "count": 18203, "self": 2.434252762989786, "children": { "TorchPolicy.evaluate": { "total": 130.61241846101166, "count": 18203, "self": 130.61241846101166 } } }, "workers": { "total": 0.320532375993821, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 494.87156265100487, "count": 18203, "is_parallel": true, "self": 230.07636323400777, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005336979000048814, "count": 1, "is_parallel": true, "self": 0.0038219880001406636, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015149909999081501, "count": 10, "is_parallel": true, "self": 0.0015149909999081501 } } }, "UnityEnvironment.step": { "total": 0.039103833000012855, "count": 1, "is_parallel": true, "self": 0.000597422999931041, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029780800002754404, "count": 1, "is_parallel": true, "self": 0.00029780800002754404 }, "communicator.exchange": { "total": 0.03614580800001477, "count": 1, "is_parallel": true, "self": 0.03614580800001477 }, "steps_from_proto": { "total": 0.002062794000039503, "count": 1, "is_parallel": true, "self": 0.0004262799998286937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016365140002108092, "count": 10, "is_parallel": true, "self": 0.0016365140002108092 } } } } } } }, "UnityEnvironment.step": { "total": 264.7951994169971, "count": 18202, "is_parallel": true, "self": 10.439190985978712, "children": { "UnityEnvironment._generate_step_input": { "total": 5.483620083014898, "count": 18202, "is_parallel": true, "self": 5.483620083014898 }, "communicator.exchange": { "total": 215.60193182299759, "count": 18202, "is_parallel": true, "self": 215.60193182299759 }, "steps_from_proto": { "total": 33.2704565250059, "count": 18202, "is_parallel": true, "self": 6.8914054230323245, "children": { "_process_rank_one_or_two_observation": { "total": 26.379051101973573, "count": 182020, "is_parallel": true, "self": 26.379051101973573 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010625300001265714, "count": 1, "self": 0.00010625300001265714, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 483.53173438301906, "count": 445504, "is_parallel": true, "self": 10.829860234054195, "children": { "process_trajectory": { "total": 270.5349741989646, "count": 445504, "is_parallel": true, "self": 269.4520938849646, "children": { "RLTrainer._checkpoint": { "total": 1.0828803140000218, "count": 4, "is_parallel": true, "self": 1.0828803140000218 } } }, "_update_policy": { "total": 202.16689995000024, "count": 90, "is_parallel": true, "self": 69.88226442300117, "children": { "TorchPPOOptimizer.update": { "total": 132.28463552699907, "count": 4584, "is_parallel": true, "self": 132.28463552699907 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13624499000002288, "count": 1, "self": 0.0008943590000853874, "children": { "RLTrainer._checkpoint": { "total": 0.1353506309999375, "count": 1, "self": 0.1353506309999375 } } } } } } }