{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30219772458076477, "min": 0.30219772458076477, "max": 1.510560154914856, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9046.5908203125, "min": 9046.5908203125, "max": 45824.3515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.579782247543335, "min": -0.12576620280742645, "max": 0.6870146989822388, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.0198974609375, "min": -30.309654235839844, "max": 198.5472412109375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00460265576839447, "min": -0.013899608515202999, "max": 0.3560936450958252, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.270332932472229, "min": -3.808492660522461, "max": 84.39419555664062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06412193066685419, "min": 0.06412193066685419, "max": 0.07304017345048618, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8977070293359587, "min": 0.5038875474433292, "max": 1.0780258926097304, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014830339160197216, "min": 0.0013125254929283884, "max": 0.0171280674005088, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20762474824276103, "min": 0.013144278511290818, "max": 0.25264761176852824, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.497761786492855e-06, "min": 7.497761786492855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010496866501089997, "min": 0.00010496866501089997, "max": 0.0036343975885341994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249922142857144, "min": 0.10249922142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349891000000001, "min": 1.3886848, "max": 2.6114658, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002596722207142857, "min": 0.0002596722207142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036354110899999995, "min": 0.0036354110899999995, "max": 0.12116543342, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012982265092432499, "min": 0.012982265092432499, "max": 0.340162992477417, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18175171315670013, "min": 0.18175171315670013, "max": 2.381140947341919, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 318.9130434782609, "min": 281.1650485436893, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29340.0, "min": 15984.0, "max": 34119.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6376021608062412, "min": -1.0000000521540642, "max": 1.694071684102967, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.6593987941742, "min": -30.51480171829462, "max": 179.5715985149145, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6376021608062412, "min": -1.0000000521540642, "max": 1.694071684102967, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.6593987941742, "min": -30.51480171829462, "max": 179.5715985149145, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0430036942523894, "min": 0.040154504425409646, "max": 6.627714531496167, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.956339871219825, "min": 3.956339871219825, "max": 106.04343250393867, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693539788", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1693542096" }, "total": 2307.877848001, "count": 1, "self": 0.8951084099999207, "children": { "run_training.setup": { "total": 0.06799765400000979, "count": 1, "self": 0.06799765400000979 }, "TrainerController.start_learning": { "total": 2306.914741937, "count": 1, "self": 1.471340066945686, "children": { "TrainerController._reset_env": { "total": 4.244086603000142, "count": 1, "self": 4.244086603000142 }, "TrainerController.advance": { "total": 2301.050322557055, "count": 64071, "self": 1.4358751979243607, "children": { "env_step": { "total": 1626.5066152570585, "count": 64071, "self": 1511.7954422050889, "children": { "SubprocessEnvManager._take_step": { "total": 113.82827083999246, "count": 64071, "self": 4.882994778959073, "children": { "TorchPolicy.evaluate": { "total": 108.94527606103338, "count": 62561, "self": 108.94527606103338 } } }, "workers": { "total": 0.8829022119771253, "count": 64071, "self": 0.0, "children": { "worker_root": { "total": 2301.502854981029, "count": 64071, "is_parallel": true, "self": 910.222838940033, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018659039997146465, "count": 1, "is_parallel": true, "self": 0.0005721729994547786, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012937310002598679, "count": 8, "is_parallel": true, "self": 0.0012937310002598679 } } }, "UnityEnvironment.step": { "total": 0.05028591000018423, "count": 1, "is_parallel": true, "self": 0.0005801690003863769, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004843820001951826, "count": 1, "is_parallel": true, "self": 0.0004843820001951826 }, "communicator.exchange": { "total": 0.047238717999789515, "count": 1, "is_parallel": true, "self": 0.047238717999789515 }, "steps_from_proto": { "total": 0.0019826409998131567, "count": 1, "is_parallel": true, "self": 0.0004039189998366055, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015787219999765512, "count": 8, "is_parallel": true, "self": 0.0015787219999765512 } } } } } } }, "UnityEnvironment.step": { "total": 1391.280016040996, "count": 64070, "is_parallel": true, "self": 34.24424050002517, "children": { "UnityEnvironment._generate_step_input": { "total": 24.189552404988262, "count": 64070, "is_parallel": true, "self": 24.189552404988262 }, "communicator.exchange": { "total": 1222.1458849050287, "count": 64070, "is_parallel": true, "self": 1222.1458849050287 }, "steps_from_proto": { "total": 110.700338230954, "count": 64070, "is_parallel": true, "self": 22.48854190003067, "children": { "_process_rank_one_or_two_observation": { "total": 88.21179633092333, "count": 512560, "is_parallel": true, "self": 88.21179633092333 } } } } } } } } } } }, "trainer_advance": { "total": 673.1078321020723, "count": 64071, "self": 2.7263027011017584, "children": { "process_trajectory": { "total": 118.52650720996735, "count": 64071, "self": 118.25014296396739, "children": { "RLTrainer._checkpoint": { "total": 0.27636424599995735, "count": 2, "self": 0.27636424599995735 } } }, "_update_policy": { "total": 551.8550221910032, "count": 454, "self": 358.89216551099344, "children": { "TorchPPOOptimizer.update": { "total": 192.96285668000974, "count": 22791, "self": 192.96285668000974 } } } } } } }, "trainer_threads": { "total": 1.4600000213249587e-06, "count": 1, "self": 1.4600000213249587e-06 }, "TrainerController._save_models": { "total": 0.14899124999919877, "count": 1, "self": 0.001927782998791372, "children": { "RLTrainer._checkpoint": { "total": 0.1470634670004074, "count": 1, "self": 0.1470634670004074 } } } } } } }