{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0545823574066162, "min": 1.0545823574066162, "max": 2.855123281478882, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10069.15234375, "min": 10069.15234375, "max": 29207.91015625, "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": 11.705409049987793, "min": 0.3756491541862488, "max": 11.705409049987793, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2282.5546875, "min": 72.87593841552734, "max": 2328.41455078125, "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": 0.06490919476709679, "min": 0.06090697954099525, "max": 0.07716469793562211, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25963677906838717, "min": 0.243627918163981, "max": 0.3578661962789792, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17707195746548038, "min": 0.11574301503110201, "max": 0.2833252596358458, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7082878298619215, "min": 0.46297206012440806, "max": 1.416626298179229, "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": 23.613636363636363, "min": 3.4318181818181817, "max": 23.613636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1039.0, "min": 151.0, "max": 1264.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.613636363636363, "min": 3.4318181818181817, "max": 23.613636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1039.0, "min": 151.0, "max": 1264.0, "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": "1716188307", "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": "1716188801" }, "total": 494.474237075, "count": 1, "self": 0.4878294940000387, "children": { "run_training.setup": { "total": 0.0990950980000207, "count": 1, "self": 0.0990950980000207 }, "TrainerController.start_learning": { "total": 493.88731248299996, "count": 1, "self": 0.6307761260034681, "children": { "TrainerController._reset_env": { "total": 3.541819499999974, "count": 1, "self": 3.541819499999974 }, "TrainerController.advance": { "total": 489.60065274999664, "count": 18199, "self": 0.30879148100279963, "children": { "env_step": { "total": 489.29186126899384, "count": 18199, "self": 322.3828075339908, "children": { "SubprocessEnvManager._take_step": { "total": 166.59271647500776, "count": 18199, "self": 1.620833096011438, "children": { "TorchPolicy.evaluate": { "total": 164.97188337899632, "count": 18199, "self": 164.97188337899632 } } }, "workers": { "total": 0.3163372599952936, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 492.626336026002, "count": 18199, "is_parallel": true, "self": 247.2350361019997, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009798606999993353, "count": 1, "is_parallel": true, "self": 0.006372520000127224, "children": { "_process_rank_one_or_two_observation": { "total": 0.003426086999866129, "count": 10, "is_parallel": true, "self": 0.003426086999866129 } } }, "UnityEnvironment.step": { "total": 0.03992122099998596, "count": 1, "is_parallel": true, "self": 0.0007331410000119831, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004047079999622838, "count": 1, "is_parallel": true, "self": 0.0004047079999622838 }, "communicator.exchange": { "total": 0.03670941600000788, "count": 1, "is_parallel": true, "self": 0.03670941600000788 }, "steps_from_proto": { "total": 0.002073956000003818, "count": 1, "is_parallel": true, "self": 0.0004006479998679424, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016733080001358758, "count": 10, "is_parallel": true, "self": 0.0016733080001358758 } } } } } } }, "UnityEnvironment.step": { "total": 245.39129992400228, "count": 18198, "is_parallel": true, "self": 11.261656235004182, "children": { "UnityEnvironment._generate_step_input": { "total": 5.684915710998666, "count": 18198, "is_parallel": true, "self": 5.684915710998666 }, "communicator.exchange": { "total": 192.77549955099812, "count": 18198, "is_parallel": true, "self": 192.77549955099812 }, "steps_from_proto": { "total": 35.669228427001315, "count": 18198, "is_parallel": true, "self": 6.922898331986232, "children": { "_process_rank_one_or_two_observation": { "total": 28.746330095015082, "count": 181980, "is_parallel": true, "self": 28.746330095015082 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015712799995526439, "count": 1, "self": 0.00015712799995526439, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 483.69868971100595, "count": 705017, "is_parallel": true, "self": 15.237429225024925, "children": { "process_trajectory": { "total": 267.09429152798054, "count": 705017, "is_parallel": true, "self": 266.2005752609805, "children": { "RLTrainer._checkpoint": { "total": 0.8937162670000589, "count": 4, "is_parallel": true, "self": 0.8937162670000589 } } }, "_update_policy": { "total": 201.36696895800048, "count": 90, "is_parallel": true, "self": 65.64455793899941, "children": { "TorchPPOOptimizer.update": { "total": 135.72241101900107, "count": 4584, "is_parallel": true, "self": 135.72241101900107 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1139069789999212, "count": 1, "self": 0.0011005259999592454, "children": { "RLTrainer._checkpoint": { "total": 0.11280645299996195, "count": 1, "self": 0.11280645299996195 } } } } } } }