{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0307931900024414, "min": 0.9445683360099792, "max": 1.4617441892623901, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 30874.318359375, "min": 28291.7109375, "max": 44343.47265625, "count": 3 }, "Pyramids.Step.mean": { "value": 89888.0, "min": 29952.0, "max": 89888.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89888.0, "min": 29952.0, "max": 89888.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09728601574897766, "min": -0.23202307522296906, "max": -0.09728601574897766, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -23.348644256591797, "min": -54.98946762084961, "max": -23.348644256591797, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1619967669248581, "min": 0.1619967669248581, "max": 0.29302218556404114, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 38.87922286987305, "min": 38.87922286987305, "max": 70.13727569580078, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06808813516296819, "min": 0.06808813516296819, "max": 0.0733561234391459, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6808813516296819, "min": 0.5073471987587714, "max": 0.6808813516296819, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0008742923530273486, "min": 0.0008742923530273486, "max": 0.008278111200221852, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.008742923530273486, "min": 0.008742923530273486, "max": 0.05794677840155297, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.80432739856e-05, "min": 7.80432739856e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000780432739856, "min": 0.000780432739856, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12601440000000003, "min": 0.12601440000000003, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.2601440000000002, "min": 1.234912, "max": 1.2868480000000002, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0026088385599999995, "min": 0.0026088385599999995, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.026088385599999996, "min": 0.026088385599999996, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.10714844614267349, "min": 0.10714844614267349, "max": 0.45613914728164673, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.0714844465255737, "min": 1.0714844465255737, "max": 3.192974090576172, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 997.5, "min": 978.8787878787879, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31920.0, "min": 15984.0, "max": 32303.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9359438039828092, "min": -1.0000000521540642, "max": -0.9192424714565277, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -29.950201727449894, "min": -30.335001558065414, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9359438039828092, "min": -1.0000000521540642, "max": -0.9192424714565277, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -29.950201727449894, "min": -30.335001558065414, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.252864717738703, "min": 1.252864717738703, "max": 9.333736169151962, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 40.09167096763849, "min": 40.09167096763849, "max": 149.3397787064314, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715938812", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715939086" }, "total": 274.692146288, "count": 1, "self": 0.529008402000045, "children": { "run_training.setup": { "total": 0.09010310100006791, "count": 1, "self": 0.09010310100006791 }, "TrainerController.start_learning": { "total": 274.0730347849999, "count": 1, "self": 0.20235360701713034, "children": { "TrainerController._reset_env": { "total": 2.4943681779998315, "count": 1, "self": 2.4943681779998315 }, "TrainerController.advance": { "total": 271.2882538579829, "count": 6259, "self": 0.21224610498484253, "children": { "env_step": { "total": 166.11827408500085, "count": 6259, "self": 151.3339588529982, "children": { "SubprocessEnvManager._take_step": { "total": 14.662845279993007, "count": 6259, "self": 0.6101162039808514, "children": { "TorchPolicy.evaluate": { "total": 14.052729076012156, "count": 6256, "self": 14.052729076012156 } } }, "workers": { "total": 0.12146995200964739, "count": 6259, "self": 0.0, "children": { "worker_root": { "total": 273.394026755999, "count": 6259, "is_parallel": true, "self": 137.35727957400013, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002981971000053818, "count": 1, "is_parallel": true, "self": 0.0010457759999553673, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019361950000984507, "count": 8, "is_parallel": true, "self": 0.0019361950000984507 } } }, "UnityEnvironment.step": { "total": 0.05428578600003675, "count": 1, "is_parallel": true, "self": 0.000679080000054455, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045194300014372857, "count": 1, "is_parallel": true, "self": 0.00045194300014372857 }, "communicator.exchange": { "total": 0.0513332470000023, "count": 1, "is_parallel": true, "self": 0.0513332470000023 }, "steps_from_proto": { "total": 0.0018215159998362651, "count": 1, "is_parallel": true, "self": 0.00038358700066964957, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014379289991666155, "count": 8, "is_parallel": true, "self": 0.0014379289991666155 } } } } } } }, "UnityEnvironment.step": { "total": 136.03674718199886, "count": 6258, "is_parallel": true, "self": 4.4181820919980055, "children": { "UnityEnvironment._generate_step_input": { "total": 2.277102920002335, "count": 6258, "is_parallel": true, "self": 2.277102920002335 }, "communicator.exchange": { "total": 117.40567068799737, "count": 6258, "is_parallel": true, "self": 117.40567068799737 }, "steps_from_proto": { "total": 11.93579148200115, "count": 6258, "is_parallel": true, "self": 2.5136160779773036, "children": { "_process_rank_one_or_two_observation": { "total": 9.422175404023847, "count": 50064, "is_parallel": true, "self": 9.422175404023847 } } } } } } } } } } }, "trainer_advance": { "total": 104.95773366799722, "count": 6259, "self": 0.26564680700585086, "children": { "process_trajectory": { "total": 15.797466327991287, "count": 6259, "self": 15.797466327991287 }, "_update_policy": { "total": 88.89462053300008, "count": 29, "self": 35.65047338499721, "children": { "TorchPPOOptimizer.update": { "total": 53.24414714800287, "count": 2289, "self": 53.24414714800287 } } } } } } }, "trainer_threads": { "total": 1.314999963142327e-06, "count": 1, "self": 1.314999963142327e-06 }, "TrainerController._save_models": { "total": 0.08805782700005693, "count": 1, "self": 0.0016399819999151077, "children": { "RLTrainer._checkpoint": { "total": 0.08641784500014182, "count": 1, "self": 0.08641784500014182 } } } } } } }