{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0199086666107178, "min": 1.0199086666107178, "max": 2.873701333999634, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9738.087890625, "min": 9738.087890625, "max": 29429.57421875, "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": 12.195115089416504, "min": 0.3036651611328125, "max": 12.195115089416504, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2378.04736328125, "min": 58.911041259765625, "max": 2481.580810546875, "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": 0.0668614070346652, "min": 0.0642850917019863, "max": 0.07399863122001418, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2674456281386608, "min": 0.2571403668079452, "max": 0.3699931561000709, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17132935833697227, "min": 0.1157156774653213, "max": 0.2713544513664993, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6853174333478891, "min": 0.4628627098612852, "max": 1.3567722568324967, "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": 23.931818181818183, "min": 3.2045454545454546, "max": 23.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1053.0, "min": 141.0, "max": 1293.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.931818181818183, "min": 3.2045454545454546, "max": 23.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1053.0, "min": 141.0, "max": 1293.0, "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": "1677668375", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677668815" }, "total": 440.136693092, "count": 1, "self": 0.440570388000026, "children": { "run_training.setup": { "total": 0.1097721559999627, "count": 1, "self": 0.1097721559999627 }, "TrainerController.start_learning": { "total": 439.586350548, "count": 1, "self": 0.5208457500031614, "children": { "TrainerController._reset_env": { "total": 9.34098514599998, "count": 1, "self": 9.34098514599998 }, "TrainerController.advance": { "total": 429.6058091409967, "count": 18203, "self": 0.2595487119946256, "children": { "env_step": { "total": 429.3462604290021, "count": 18203, "self": 292.8979719140089, "children": { "SubprocessEnvManager._take_step": { "total": 136.18469383399366, "count": 18203, "self": 1.4138502299990137, "children": { "TorchPolicy.evaluate": { "total": 134.77084360399465, "count": 18203, "self": 30.003957524992074, "children": { "TorchPolicy.sample_actions": { "total": 104.76688607900257, "count": 18203, "self": 104.76688607900257 } } } } }, "workers": { "total": 0.26359468099951755, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 438.1756787570133, "count": 18203, "is_parallel": true, "self": 213.3983411410228, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006923915999948349, "count": 1, "is_parallel": true, "self": 0.004274621000092793, "children": { "_process_rank_one_or_two_observation": { "total": 0.002649294999855556, "count": 10, "is_parallel": true, "self": 0.002649294999855556 } } }, "UnityEnvironment.step": { "total": 0.04357585599996128, "count": 1, "is_parallel": true, "self": 0.0005949679999730506, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030600200000208133, "count": 1, "is_parallel": true, "self": 0.00030600200000208133 }, "communicator.exchange": { "total": 0.04082782799997631, "count": 1, "is_parallel": true, "self": 0.04082782799997631 }, "steps_from_proto": { "total": 0.001847058000009838, "count": 1, "is_parallel": true, "self": 0.00042687899997417844, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014201790000356596, "count": 10, "is_parallel": true, "self": 0.0014201790000356596 } } } } } } }, "UnityEnvironment.step": { "total": 224.77733761599052, "count": 18202, "is_parallel": true, "self": 9.060350126992716, "children": { "UnityEnvironment._generate_step_input": { "total": 4.967169830005275, "count": 18202, "is_parallel": true, "self": 4.967169830005275 }, "communicator.exchange": { "total": 181.17755779799842, "count": 18202, "is_parallel": true, "self": 181.17755779799842 }, "steps_from_proto": { "total": 29.57225986099411, "count": 18202, "is_parallel": true, "self": 6.292571262971421, "children": { "_process_rank_one_or_two_observation": { "total": 23.279688598022688, "count": 182020, "is_parallel": true, "self": 23.279688598022688 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001231470000675472, "count": 1, "self": 0.0001231470000675472, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 426.45851175305165, "count": 391201, "is_parallel": true, "self": 9.332836770036636, "children": { "process_trajectory": { "total": 244.73446624001468, "count": 391201, "is_parallel": true, "self": 243.73078124101477, "children": { "RLTrainer._checkpoint": { "total": 1.0036849989999155, "count": 4, "is_parallel": true, "self": 1.0036849989999155 } } }, "_update_policy": { "total": 172.39120874300033, "count": 90, "is_parallel": true, "self": 59.92312842399616, "children": { "TorchPPOOptimizer.update": { "total": 112.46808031900417, "count": 4587, "is_parallel": true, "self": 112.46808031900417 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11858736400006364, "count": 1, "self": 0.0009228520000306162, "children": { "RLTrainer._checkpoint": { "total": 0.11766451200003303, "count": 1, "self": 0.11766451200003303 } } } } } } }