{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8865359425544739, "min": 0.8865359425544739, "max": 2.8674285411834717, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8454.8935546875, "min": 8454.8935546875, "max": 29365.3359375, "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": 13.102118492126465, "min": 0.40484389662742615, "max": 13.102118492126465, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2554.9130859375, "min": 78.53971862792969, "max": 2665.3193359375, "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": 0.07084275143193629, "min": 0.0636858584903701, "max": 0.07592623850259948, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28337100572774515, "min": 0.2547434339614804, "max": 0.357626071139855, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1975961830101761, "min": 0.12905799689663885, "max": 0.31555733131427394, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7903847320407044, "min": 0.5162319875865554, "max": 1.5777866565713696, "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": 25.545454545454547, "min": 4.0, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1124.0, "min": 176.0, "max": 1425.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.545454545454547, "min": 4.0, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1124.0, "min": 176.0, "max": 1425.0, "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": "1687223001", "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": "1687223471" }, "total": 470.71241685300015, "count": 1, "self": 0.8419991419998496, "children": { "run_training.setup": { "total": 0.043289350000122795, "count": 1, "self": 0.043289350000122795 }, "TrainerController.start_learning": { "total": 469.8271283610002, "count": 1, "self": 0.5444432050076102, "children": { "TrainerController._reset_env": { "total": 4.180826497999988, "count": 1, "self": 4.180826497999988 }, "TrainerController.advance": { "total": 464.8812328859924, "count": 18209, "self": 0.25663818497855573, "children": { "env_step": { "total": 464.62459470101385, "count": 18209, "self": 342.1357233350177, "children": { "SubprocessEnvManager._take_step": { "total": 122.22314887400307, "count": 18209, "self": 1.6764102440267834, "children": { "TorchPolicy.evaluate": { "total": 120.54673862997629, "count": 18209, "self": 120.54673862997629 } } }, "workers": { "total": 0.2657224919930741, "count": 18209, "self": 0.0, "children": { "worker_root": { "total": 468.2216159179677, "count": 18209, "is_parallel": true, "self": 217.45074089196942, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005871605000038471, "count": 1, "is_parallel": true, "self": 0.004296466000141663, "children": { "_process_rank_one_or_two_observation": { "total": 0.001575138999896808, "count": 10, "is_parallel": true, "self": 0.001575138999896808 } } }, "UnityEnvironment.step": { "total": 0.04659999499995138, "count": 1, "is_parallel": true, "self": 0.0006160559998988901, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003064190000259259, "count": 1, "is_parallel": true, "self": 0.0003064190000259259 }, "communicator.exchange": { "total": 0.03085174700004245, "count": 1, "is_parallel": true, "self": 0.03085174700004245 }, "steps_from_proto": { "total": 0.01482577299998411, "count": 1, "is_parallel": true, "self": 0.0004151090004143043, "children": { "_process_rank_one_or_two_observation": { "total": 0.014410663999569806, "count": 10, "is_parallel": true, "self": 0.014410663999569806 } } } } } } }, "UnityEnvironment.step": { "total": 250.7708750259983, "count": 18208, "is_parallel": true, "self": 10.580150923986366, "children": { "UnityEnvironment._generate_step_input": { "total": 5.262178323985609, "count": 18208, "is_parallel": true, "self": 5.262178323985609 }, "communicator.exchange": { "total": 199.9149053040219, "count": 18208, "is_parallel": true, "self": 199.9149053040219 }, "steps_from_proto": { "total": 35.01364047400443, "count": 18208, "is_parallel": true, "self": 6.319171928062133, "children": { "_process_rank_one_or_two_observation": { "total": 28.6944685459423, "count": 182080, "is_parallel": true, "self": 28.6944685459423 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001469989999804966, "count": 1, "self": 0.0001469989999804966, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.5913647940588, "count": 428721, "is_parallel": true, "self": 9.001679323132521, "children": { "process_trajectory": { "total": 252.33345805292515, "count": 428721, "is_parallel": true, "self": 250.82490206992497, "children": { "RLTrainer._checkpoint": { "total": 1.5085559830001785, "count": 4, "is_parallel": true, "self": 1.5085559830001785 } } }, "_update_policy": { "total": 200.25622741800112, "count": 90, "is_parallel": true, "self": 79.18940380599838, "children": { "TorchPPOOptimizer.update": { "total": 121.06682361200274, "count": 4587, "is_parallel": true, "self": 121.06682361200274 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22047877300019536, "count": 1, "self": 0.001132686000346439, "children": { "RLTrainer._checkpoint": { "total": 0.21934608699984892, "count": 1, "self": 0.21934608699984892 } } } } } } }