{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9692443609237671, "min": 0.927122175693512, "max": 2.8436264991760254, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9286.330078125, "min": 8811.369140625, "max": 29152.859375, "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": 13.431455612182617, "min": 0.39277899265289307, "max": 13.490251541137695, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2619.1337890625, "min": 76.19912719726562, "max": 2752.01123046875, "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": 0.07533240765812534, "min": 0.060603809537589724, "max": 0.07533240765812534, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30132963063250134, "min": 0.2543733938678177, "max": 0.3590799850257919, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17713492524390126, "min": 0.1094620518920505, "max": 0.270675156411587, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.708539700975605, "min": 0.437848207568202, "max": 1.2626544186918467, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.6940097306000015e-05, "min": 2.6940097306000015e-05, "max": 0.000972940002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00010776038922400006, "min": 0.00010776038922400006, "max": 0.004617200038280001, "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": 26.363636363636363, "min": 3.2954545454545454, "max": 26.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1160.0, "min": 145.0, "max": 1462.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.363636363636363, "min": 3.2954545454545454, "max": 26.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1160.0, "min": 145.0, "max": 1462.0, "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": "1679909142", "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 --force", "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": "1679909616" }, "total": 474.01528819100076, "count": 1, "self": 0.9354834430005212, "children": { "run_training.setup": { "total": 0.11649593800029834, "count": 1, "self": 0.11649593800029834 }, "TrainerController.start_learning": { "total": 472.96330880999994, "count": 1, "self": 0.5450964140818542, "children": { "TrainerController._reset_env": { "total": 7.216771080000399, "count": 1, "self": 7.216771080000399 }, "TrainerController.advance": { "total": 464.9384942569177, "count": 18207, "self": 0.2670243389102325, "children": { "env_step": { "total": 464.67146991800746, "count": 18207, "self": 336.548142367089, "children": { "SubprocessEnvManager._take_step": { "total": 127.85904619493431, "count": 18207, "self": 2.3067254889247124, "children": { "TorchPolicy.evaluate": { "total": 125.5523207060096, "count": 18207, "self": 125.5523207060096 } } }, "workers": { "total": 0.264281355984167, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 471.22251515205244, "count": 18207, "is_parallel": true, "self": 228.7384939289741, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002133738999873458, "count": 1, "is_parallel": true, "self": 0.0006460940003307769, "children": { "_process_rank_one_or_two_observation": { "total": 0.001487644999542681, "count": 10, "is_parallel": true, "self": 0.001487644999542681 } } }, "UnityEnvironment.step": { "total": 0.034104481999747804, "count": 1, "is_parallel": true, "self": 0.0005338770006346749, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002983309996125172, "count": 1, "is_parallel": true, "self": 0.0002983309996125172 }, "communicator.exchange": { "total": 0.03133145199990395, "count": 1, "is_parallel": true, "self": 0.03133145199990395 }, "steps_from_proto": { "total": 0.0019408219995966647, "count": 1, "is_parallel": true, "self": 0.00039802599894755986, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015427960006491048, "count": 10, "is_parallel": true, "self": 0.0015427960006491048 } } } } } } }, "UnityEnvironment.step": { "total": 242.48402122307834, "count": 18206, "is_parallel": true, "self": 9.667503741089604, "children": { "UnityEnvironment._generate_step_input": { "total": 5.193780598013291, "count": 18206, "is_parallel": true, "self": 5.193780598013291 }, "communicator.exchange": { "total": 196.30568538498846, "count": 18206, "is_parallel": true, "self": 196.30568538498846 }, "steps_from_proto": { "total": 31.317051498986984, "count": 18206, "is_parallel": true, "self": 6.118698400159701, "children": { "_process_rank_one_or_two_observation": { "total": 25.198353098827283, "count": 182060, "is_parallel": true, "self": 25.198353098827283 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017419699997844873, "count": 1, "self": 0.00017419699997844873, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.45478128468767, "count": 409844, "is_parallel": true, "self": 10.227170245810157, "children": { "process_trajectory": { "total": 253.52621373487636, "count": 409844, "is_parallel": true, "self": 251.92142233887625, "children": { "RLTrainer._checkpoint": { "total": 1.6047913960001097, "count": 4, "is_parallel": true, "self": 1.6047913960001097 } } }, "_update_policy": { "total": 197.70139730400115, "count": 90, "is_parallel": true, "self": 73.85614802703094, "children": { "TorchPPOOptimizer.update": { "total": 123.84524927697021, "count": 4584, "is_parallel": true, "self": 123.84524927697021 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2627728620000198, "count": 1, "self": 0.0019030799994652625, "children": { "RLTrainer._checkpoint": { "total": 0.26086978200055455, "count": 1, "self": 0.26086978200055455 } } } } } } }