{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4891842007637024, "min": 0.4864496886730194, "max": 1.40961492061615, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14550.294921875, "min": 14550.294921875, "max": 42762.078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1417328417301178, "min": -0.10461755096912384, "max": 0.2163393199443817, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 35.7166748046875, "min": -25.21282958984375, "max": 55.599205017089844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01762525551021099, "min": 0.0017850169679149985, "max": 0.3551114797592163, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.441564559936523, "min": 0.4551793336868286, "max": 85.93698120117188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07041627789551604, "min": 0.06505331904937738, "max": 0.07386146823510302, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9858278905372245, "min": 0.5170302776457212, "max": 1.0411579476397796, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008685142988761208, "min": 0.0005676662027157316, "max": 0.011656984981079407, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12159200184265692, "min": 0.006617539695736713, "max": 0.1631977897351117, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.269204719821425e-06, "min": 7.269204719821425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010176886607749995, "min": 0.00010176886607749995, "max": 0.0033824849725050997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242303571428572, "min": 0.10242303571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339225000000002, "min": 1.3886848, "max": 2.5274948999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025206126785714275, "min": 0.00025206126785714275, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035288577499999986, "min": 0.0035288577499999986, "max": 0.11277674051000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012688325718045235, "min": 0.012688325718045235, "max": 0.5393239855766296, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17763656377792358, "min": 0.17763656377792358, "max": 3.775268077850342, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 723.6590909090909, "min": 552.4528301886793, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31841.0, "min": 15984.0, "max": 32933.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5488363280892372, "min": -1.0000000521540642, "max": 0.9945773306601452, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 24.148798435926437, "min": -29.977801725268364, "max": 52.7125985249877, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5488363280892372, "min": -1.0000000521540642, "max": 0.9945773306601452, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 24.148798435926437, "min": -29.977801725268364, "max": 52.7125985249877, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09604682175267953, "min": 0.07568903431243632, "max": 11.286061864346266, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.2260601571178995, "min": 3.872648993972689, "max": 180.57698982954025, "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": "1679052446", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1679054451" }, "total": 2005.49943537, "count": 1, "self": 0.42441031999942425, "children": { "run_training.setup": { "total": 0.10129927800016958, "count": 1, "self": 0.10129927800016958 }, "TrainerController.start_learning": { "total": 2004.9737257720003, "count": 1, "self": 1.3442122149617717, "children": { "TrainerController._reset_env": { "total": 7.122609523999927, "count": 1, "self": 7.122609523999927 }, "TrainerController.advance": { "total": 1996.4164098810384, "count": 63302, "self": 1.4215391701077351, "children": { "env_step": { "total": 1378.3127125399596, "count": 63302, "self": 1271.5395344079243, "children": { "SubprocessEnvManager._take_step": { "total": 105.97440320907754, "count": 63302, "self": 4.581719118059027, "children": { "TorchPolicy.evaluate": { "total": 101.39268409101851, "count": 62556, "self": 101.39268409101851 } } }, "workers": { "total": 0.7987749229578185, "count": 63302, "self": 0.0, "children": { "worker_root": { "total": 2000.7196232280012, "count": 63302, "is_parallel": true, "self": 839.9582141129495, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016882180002539826, "count": 1, "is_parallel": true, "self": 0.0005584390005424211, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011297789997115615, "count": 8, "is_parallel": true, "self": 0.0011297789997115615 } } }, "UnityEnvironment.step": { "total": 0.047266652999951475, "count": 1, "is_parallel": true, "self": 0.0005196729998715455, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044502900027509895, "count": 1, "is_parallel": true, "self": 0.00044502900027509895 }, "communicator.exchange": { "total": 0.04464610900004118, "count": 1, "is_parallel": true, "self": 0.04464610900004118 }, "steps_from_proto": { "total": 0.001655841999763652, "count": 1, "is_parallel": true, "self": 0.00034281399894098286, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013130280008226691, "count": 8, "is_parallel": true, "self": 0.0013130280008226691 } } } } } } }, "UnityEnvironment.step": { "total": 1160.7614091150517, "count": 63301, "is_parallel": true, "self": 30.328445358142744, "children": { "UnityEnvironment._generate_step_input": { "total": 22.48475628995766, "count": 63301, "is_parallel": true, "self": 22.48475628995766 }, "communicator.exchange": { "total": 1019.2240604020349, "count": 63301, "is_parallel": true, "self": 1019.2240604020349 }, "steps_from_proto": { "total": 88.72414706491645, "count": 63301, "is_parallel": true, "self": 18.813858682070986, "children": { "_process_rank_one_or_two_observation": { "total": 69.91028838284547, "count": 506408, "is_parallel": true, "self": 69.91028838284547 } } } } } } } } } } }, "trainer_advance": { "total": 616.682158170971, "count": 63302, "self": 2.392213496074419, "children": { "process_trajectory": { "total": 112.86689937990195, "count": 63302, "self": 112.67104041690209, "children": { "RLTrainer._checkpoint": { "total": 0.19585896299986416, "count": 2, "self": 0.19585896299986416 } } }, "_update_policy": { "total": 501.4230452949946, "count": 444, "self": 317.78075527905276, "children": { "TorchPPOOptimizer.update": { "total": 183.64229001594185, "count": 22785, "self": 183.64229001594185 } } } } } } }, "trainer_threads": { "total": 1.0530002327868715e-06, "count": 1, "self": 1.0530002327868715e-06 }, "TrainerController._save_models": { "total": 0.0904930990000139, "count": 1, "self": 0.0018201189996034373, "children": { "RLTrainer._checkpoint": { "total": 0.08867298000041046, "count": 1, "self": 0.08867298000041046 } } } } } } }