{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.081977128982544, "min": 1.081977128982544, "max": 2.855358839035034, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10330.7177734375, "min": 10330.7177734375, "max": 29241.73046875, "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": 13.133866310119629, "min": 0.33693596720695496, "max": 13.133866310119629, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2561.10400390625, "min": 65.3655776977539, "max": 2660.630615234375, "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": 0.06554590235828073, "min": 0.06141091940582341, "max": 0.07310232228209154, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2621836094331229, "min": 0.24564367762329364, "max": 0.36551161141045774, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21595617657636895, "min": 0.12116885256717283, "max": 0.2965412577285486, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8638247063054758, "min": 0.4846754102686913, "max": 1.4827062886427431, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.0776097306000009e-05, "min": 1.0776097306000009e-05, "max": 0.000389176002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.3104389224000035e-05, "min": 4.3104389224000035e-05, "max": 0.0018468800382800002, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.9617200000000001, "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": 0.023089828000000003, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.727272727272727, "min": 3.7045454545454546, "max": 26.12727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 163.0, "max": 1437.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.7045454545454546, "max": 26.12727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 163.0, "max": 1437.0, "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": "1679307174", "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": "1679307691" }, "total": 517.1323006350001, "count": 1, "self": 0.43211895700017067, "children": { "run_training.setup": { "total": 0.10514019000004282, "count": 1, "self": 0.10514019000004282 }, "TrainerController.start_learning": { "total": 516.5950414879999, "count": 1, "self": 0.5760805789894903, "children": { "TrainerController._reset_env": { "total": 10.358029982999938, "count": 1, "self": 10.358029982999938 }, "TrainerController.advance": { "total": 505.5194288790103, "count": 18201, "self": 0.2994573289956861, "children": { "env_step": { "total": 505.21997155001463, "count": 18201, "self": 371.39660851302233, "children": { "SubprocessEnvManager._take_step": { "total": 133.54428674297833, "count": 18201, "self": 2.1186576619716107, "children": { "TorchPolicy.evaluate": { "total": 131.42562908100672, "count": 18201, "self": 131.42562908100672 } } }, "workers": { "total": 0.2790762940139757, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 514.9266196729905, "count": 18201, "is_parallel": true, "self": 263.6994217679951, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005627452999988236, "count": 1, "is_parallel": true, "self": 0.004037738999954854, "children": { "_process_rank_one_or_two_observation": { "total": 0.001589714000033382, "count": 10, "is_parallel": true, "self": 0.001589714000033382 } } }, "UnityEnvironment.step": { "total": 0.037078744000154984, "count": 1, "is_parallel": true, "self": 0.00060438300010901, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045074700005898194, "count": 1, "is_parallel": true, "self": 0.00045074700005898194 }, "communicator.exchange": { "total": 0.03397898399998667, "count": 1, "is_parallel": true, "self": 0.03397898399998667 }, "steps_from_proto": { "total": 0.002044630000000325, "count": 1, "is_parallel": true, "self": 0.00041361200010214816, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016310179998981766, "count": 10, "is_parallel": true, "self": 0.0016310179998981766 } } } } } } }, "UnityEnvironment.step": { "total": 251.22719790499536, "count": 18200, "is_parallel": true, "self": 10.038808819992482, "children": { "UnityEnvironment._generate_step_input": { "total": 5.580484879999176, "count": 18200, "is_parallel": true, "self": 5.580484879999176 }, "communicator.exchange": { "total": 201.86685442198632, "count": 18200, "is_parallel": true, "self": 201.86685442198632 }, "steps_from_proto": { "total": 33.74104978301739, "count": 18200, "is_parallel": true, "self": 6.941218813071828, "children": { "_process_rank_one_or_two_observation": { "total": 26.79983096994556, "count": 182000, "is_parallel": true, "self": 26.79983096994556 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010194200012847432, "count": 1, "self": 0.00010194200012847432, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 501.5445581001038, "count": 421299, "is_parallel": true, "self": 10.876799148078362, "children": { "process_trajectory": { "total": 262.66875924202714, "count": 421299, "is_parallel": true, "self": 261.54166943502696, "children": { "RLTrainer._checkpoint": { "total": 1.127089807000175, "count": 4, "is_parallel": true, "self": 1.127089807000175 } } }, "_update_policy": { "total": 227.99899970999832, "count": 90, "is_parallel": true, "self": 89.02975011899343, "children": { "TorchPPOOptimizer.update": { "total": 138.96924959100488, "count": 6116, "is_parallel": true, "self": 138.96924959100488 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14140010500000244, "count": 1, "self": 0.0008762459999616112, "children": { "RLTrainer._checkpoint": { "total": 0.14052385900004083, "count": 1, "self": 0.14052385900004083 } } } } } } }