{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.089093565940857, "min": 1.089093565940857, "max": 2.8720476627349854, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10422.625, "min": 10422.625, "max": 29507.41796875, "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": 12.608010292053223, "min": 0.4004248380661011, "max": 12.608010292053223, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2458.56201171875, "min": 77.68241882324219, "max": 2539.078125, "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": 0.06702485541680682, "min": 0.06500242777241796, "max": 0.07451905159453186, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2680994216672273, "min": 0.26224351049270755, "max": 0.3725952579726593, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24288431788776438, "min": 0.14107672414998068, "max": 0.27186336346408896, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9715372715510575, "min": 0.5643068965999227, "max": 1.3593168173204448, "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": 24.59090909090909, "min": 3.8636363636363638, "max": 25.2, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1082.0, "min": 170.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.59090909090909, "min": 3.8636363636363638, "max": 25.2, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1082.0, "min": 170.0, "max": 1386.0, "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": "1686687341", "python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/salmamun/miniconda3/envs/hf/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": "1686688212" }, "total": 870.372882300002, "count": 1, "self": 0.47485580000284244, "children": { "run_training.setup": { "total": 0.021354900000005728, "count": 1, "self": 0.021354900000005728 }, "TrainerController.start_learning": { "total": 869.8766715999991, "count": 1, "self": 0.8355214004368463, "children": { "TrainerController._reset_env": { "total": 4.5700010000000475, "count": 1, "self": 4.5700010000000475 }, "TrainerController.advance": { "total": 864.292764899561, "count": 18201, "self": 0.4165867989140679, "children": { "env_step": { "total": 863.8761781006469, "count": 18201, "self": 519.7847504017991, "children": { "SubprocessEnvManager._take_step": { "total": 343.75569939925845, "count": 18201, "self": 2.6432609991279605, "children": { "TorchPolicy.evaluate": { "total": 341.1124384001305, "count": 18201, "self": 341.1124384001305 } } }, "workers": { "total": 0.3357282995893911, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 868.2391612997017, "count": 18201, "is_parallel": true, "self": 492.0498041999599, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025076999991142657, "count": 1, "is_parallel": true, "self": 0.0008736999916436616, "children": { "_process_rank_one_or_two_observation": { "total": 0.001634000007470604, "count": 10, "is_parallel": true, "self": 0.001634000007470604 } } }, "UnityEnvironment.step": { "total": 0.04619209999873419, "count": 1, "is_parallel": true, "self": 0.0004974000039510429, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028109999766456895, "count": 1, "is_parallel": true, "self": 0.00028109999766456895 }, "communicator.exchange": { "total": 0.04418449999866425, "count": 1, "is_parallel": true, "self": 0.04418449999866425 }, "steps_from_proto": { "total": 0.0012290999984543305, "count": 1, "is_parallel": true, "self": 0.0002523000002838671, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009767999981704634, "count": 10, "is_parallel": true, "self": 0.0009767999981704634 } } } } } } }, "UnityEnvironment.step": { "total": 376.18935709974176, "count": 18200, "is_parallel": true, "self": 8.407305899891071, "children": { "UnityEnvironment._generate_step_input": { "total": 5.004293600439269, "count": 18200, "is_parallel": true, "self": 5.004293600439269 }, "communicator.exchange": { "total": 337.6773151000489, "count": 18200, "is_parallel": true, "self": 337.6773151000489 }, "steps_from_proto": { "total": 25.100442499362543, "count": 18200, "is_parallel": true, "self": 5.822899298636912, "children": { "_process_rank_one_or_two_observation": { "total": 19.27754320072563, "count": 182000, "is_parallel": true, "self": 19.27754320072563 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013210000179242343, "count": 1, "self": 0.00013210000179242343, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 855.7088157008766, "count": 667283, "is_parallel": true, "self": 24.961665402108338, "children": { "process_trajectory": { "total": 458.36312329875, "count": 667283, "is_parallel": true, "self": 457.32563419874714, "children": { "RLTrainer._checkpoint": { "total": 1.0374891000028583, "count": 4, "is_parallel": true, "self": 1.0374891000028583 } } }, "_update_policy": { "total": 372.38402700001825, "count": 90, "is_parallel": true, "self": 46.27075940002396, "children": { "TorchPPOOptimizer.update": { "total": 326.1132675999943, "count": 4581, "is_parallel": true, "self": 326.1132675999943 } } } } } } } } }, "TrainerController._save_models": { "total": 0.178252199999406, "count": 1, "self": 0.0012702999956673011, "children": { "RLTrainer._checkpoint": { "total": 0.1769819000037387, "count": 1, "self": 0.1769819000037387 } } } } } } }