{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9071975350379944, "min": 0.9071975350379944, "max": 2.862398147583008, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8661.921875, "min": 8661.921875, "max": 29313.8203125, "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": 13.31387996673584, "min": 0.31699860095977783, "max": 13.31387996673584, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2596.20654296875, "min": 61.49773025512695, "max": 2708.628662109375, "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": 0.09586794464800785, "min": 0.0879616845788191, "max": 0.10309569885584471, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3834717785920314, "min": 0.3518467383152764, "max": 0.5154784942792235, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21702706861291446, "min": 0.12647287684741232, "max": 0.2865125051608272, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8681082744516578, "min": 0.5058915073896493, "max": 1.4325625258041361, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.0013852560382479997, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999997, "min": 0.10269399999999997, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077599999999986, "min": 0.41077599999999986, "max": 0.9617520000000002, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023091424800000003, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.09090909090909, "min": 3.7045454545454546, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1148.0, "min": 163.0, "max": 1432.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.09090909090909, "min": 3.7045454545454546, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1148.0, "min": 163.0, "max": 1432.0, "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": "1711616380", "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-executable/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --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": "1711616867" }, "total": 486.534924175, "count": 1, "self": 0.47664410099991983, "children": { "run_training.setup": { "total": 0.04938678500002425, "count": 1, "self": 0.04938678500002425 }, "TrainerController.start_learning": { "total": 486.00889328900007, "count": 1, "self": 0.5362556049947216, "children": { "TrainerController._reset_env": { "total": 2.608999036000114, "count": 1, "self": 2.608999036000114 }, "TrainerController.advance": { "total": 482.7654540670053, "count": 18200, "self": 0.2518976510232278, "children": { "env_step": { "total": 482.51355641598207, "count": 18200, "self": 336.96905178602356, "children": { "SubprocessEnvManager._take_step": { "total": 145.26210134097914, "count": 18200, "self": 1.4120376279533957, "children": { "TorchPolicy.evaluate": { "total": 143.85006371302575, "count": 18200, "self": 143.85006371302575 } } }, "workers": { "total": 0.28240328897936706, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 484.81923602101006, "count": 18200, "is_parallel": true, "self": 264.5075217580229, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005408613000099649, "count": 1, "is_parallel": true, "self": 0.003939227000273604, "children": { "_process_rank_one_or_two_observation": { "total": 0.001469385999826045, "count": 10, "is_parallel": true, "self": 0.001469385999826045 } } }, "UnityEnvironment.step": { "total": 0.041220984999881694, "count": 1, "is_parallel": true, "self": 0.0007587719999264664, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039409700002579484, "count": 1, "is_parallel": true, "self": 0.00039409700002579484 }, "communicator.exchange": { "total": 0.0375861499999246, "count": 1, "is_parallel": true, "self": 0.0375861499999246 }, "steps_from_proto": { "total": 0.0024819660000048316, "count": 1, "is_parallel": true, "self": 0.00043705200027943647, "children": { "_process_rank_one_or_two_observation": { "total": 0.002044913999725395, "count": 10, "is_parallel": true, "self": 0.002044913999725395 } } } } } } }, "UnityEnvironment.step": { "total": 220.31171426298715, "count": 18199, "is_parallel": true, "self": 10.088796717986725, "children": { "UnityEnvironment._generate_step_input": { "total": 5.344474010007389, "count": 18199, "is_parallel": true, "self": 5.344474010007389 }, "communicator.exchange": { "total": 171.42248616400093, "count": 18199, "is_parallel": true, "self": 171.42248616400093 }, "steps_from_proto": { "total": 33.45595737099211, "count": 18199, "is_parallel": true, "self": 6.17649148102123, "children": { "_process_rank_one_or_two_observation": { "total": 27.27946588997088, "count": 181990, "is_parallel": true, "self": 27.27946588997088 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012042599996675563, "count": 1, "self": 0.00012042599996675563, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 477.61683979501254, "count": 635741, "is_parallel": true, "self": 13.563467981067106, "children": { "process_trajectory": { "total": 240.84199563594575, "count": 635741, "is_parallel": true, "self": 240.2667994899457, "children": { "RLTrainer._checkpoint": { "total": 0.575196146000053, "count": 4, "is_parallel": true, "self": 0.575196146000053 } } }, "_update_policy": { "total": 223.21137617799968, "count": 90, "is_parallel": true, "self": 50.01611131099321, "children": { "TorchPPOOptimizer.update": { "total": 173.19526486700647, "count": 9177, "is_parallel": true, "self": 173.19526486700647 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09806415499997456, "count": 1, "self": 0.0010137770000255841, "children": { "RLTrainer._checkpoint": { "total": 0.09705037799994898, "count": 1, "self": 0.09705037799994898 } } } } } } }