{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8986561894416809, "min": 0.8986561894416809, "max": 2.8716650009155273, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8580.369140625, "min": 8580.369140625, "max": 29535.07421875, "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": 12.974709510803223, "min": 0.2676580250263214, "max": 13.014567375183105, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2530.068359375, "min": 51.9256591796875, "max": 2654.9716796875, "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": 0.06809029484757761, "min": 0.061514649225921626, "max": 0.07948633022343868, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27236117939031046, "min": 0.24609189831538542, "max": 0.39743165111719336, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20496094789282948, "min": 0.12908740417675718, "max": 0.2863588478489249, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8198437915713179, "min": 0.5163496167070287, "max": 1.3715339305938459, "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": 25.15909090909091, "min": 3.5, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 154.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.5, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 154.0, "max": 1405.0, "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": "1723385692", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723386163" }, "total": 471.0462902080001, "count": 1, "self": 0.48606076800001574, "children": { "run_training.setup": { "total": 0.07093999400001394, "count": 1, "self": 0.07093999400001394 }, "TrainerController.start_learning": { "total": 470.48928944600004, "count": 1, "self": 0.5856696610184144, "children": { "TrainerController._reset_env": { "total": 3.557010267999999, "count": 1, "self": 3.557010267999999 }, "TrainerController.advance": { "total": 466.2405171349816, "count": 18201, "self": 0.27856394598848055, "children": { "env_step": { "total": 465.9619531889931, "count": 18201, "self": 302.28292957698136, "children": { "SubprocessEnvManager._take_step": { "total": 163.381338550009, "count": 18201, "self": 1.565804845004891, "children": { "TorchPolicy.evaluate": { "total": 161.8155337050041, "count": 18201, "self": 161.8155337050041 } } }, "workers": { "total": 0.29768506200275624, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 469.36932161200275, "count": 18201, "is_parallel": true, "self": 236.457620274997, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006102231999989272, "count": 1, "is_parallel": true, "self": 0.0045054379999101, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015967940000791714, "count": 10, "is_parallel": true, "self": 0.0015967940000791714 } } }, "UnityEnvironment.step": { "total": 0.03803125500007809, "count": 1, "is_parallel": true, "self": 0.0006584210001392421, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043077899999843794, "count": 1, "is_parallel": true, "self": 0.00043077899999843794 }, "communicator.exchange": { "total": 0.03480987199998253, "count": 1, "is_parallel": true, "self": 0.03480987199998253 }, "steps_from_proto": { "total": 0.0021321829999578767, "count": 1, "is_parallel": true, "self": 0.0003942230000575364, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017379599999003403, "count": 10, "is_parallel": true, "self": 0.0017379599999003403 } } } } } } }, "UnityEnvironment.step": { "total": 232.91170133700575, "count": 18200, "is_parallel": true, "self": 10.663751445019443, "children": { "UnityEnvironment._generate_step_input": { "total": 5.507414492990392, "count": 18200, "is_parallel": true, "self": 5.507414492990392 }, "communicator.exchange": { "total": 182.12427844299464, "count": 18200, "is_parallel": true, "self": 182.12427844299464 }, "steps_from_proto": { "total": 34.61625695600128, "count": 18200, "is_parallel": true, "self": 6.4896851499994455, "children": { "_process_rank_one_or_two_observation": { "total": 28.126571806001834, "count": 182000, "is_parallel": true, "self": 28.126571806001834 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014498199993795424, "count": 1, "self": 0.00014498199993795424, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 460.30555150493865, "count": 706841, "is_parallel": true, "self": 15.020031112861375, "children": { "process_trajectory": { "total": 253.76446284607778, "count": 706841, "is_parallel": true, "self": 252.6951501490778, "children": { "RLTrainer._checkpoint": { "total": 1.0693126969999867, "count": 4, "is_parallel": true, "self": 1.0693126969999867 } } }, "_update_policy": { "total": 191.5210575459995, "count": 90, "is_parallel": true, "self": 61.848418140994454, "children": { "TorchPPOOptimizer.update": { "total": 129.67263940500504, "count": 4587, "is_parallel": true, "self": 129.67263940500504 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10594740000010461, "count": 1, "self": 0.0010378630001923739, "children": { "RLTrainer._checkpoint": { "total": 0.10490953699991223, "count": 1, "self": 0.10490953699991223 } } } } } } }