{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.0955950915813446, "min": 0.09436549991369247, "max": 1.3554917573928833, "count": 333 }, "Pyramids.Policy.Entropy.sum": { "value": 2840.3212890625, "min": 2833.984619140625, "max": 41120.19921875, "count": 333 }, "Pyramids.Step.mean": { "value": 9989901.0, "min": 29980.0, "max": 9989901.0, "count": 333 }, "Pyramids.Step.sum": { "value": 9989901.0, "min": 29980.0, "max": 9989901.0, "count": 333 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.9043908715248108, "min": -0.11052733659744263, "max": 0.9892714023590088, "count": 333 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 283.0743408203125, "min": -26.637088775634766, "max": 315.57757568359375, "count": 333 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004980965051800013, "min": -0.045170947909355164, "max": 0.6073437929153442, "count": 333 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.5590420961380005, "min": -13.280258178710938, "max": 144.54782104492188, "count": 333 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06626909062227546, "min": 0.06334194002279435, "max": 0.07505433494494172, "count": 333 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9277672687118563, "min": 0.5652185566612553, "max": 1.08269119888713, "count": 333 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013294236297952013, "min": 0.0004800667355683263, "max": 0.022125206542101213, "count": 333 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18611930817132818, "min": 0.0062408675623882425, "max": 0.24089624340801188, "count": 333 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.286390428678534e-07, "min": 7.286390428678534e-07, "max": 0.00029952244515918494, "count": 333 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.0200946600149948e-05, "min": 1.0200946600149948e-05, "max": 0.004169206010264699, "count": 333 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10024284642857142, "min": 0.10024284642857142, "max": 0.199840815, "count": 333 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.40339985, "min": 1.40339985, "max": 2.8897353000000003, "count": 333 }, "Pyramids.Policy.Beta.mean": { "value": 3.4260358214285587e-05, "min": 3.4260358214285587e-05, "max": 0.0099840974185, "count": 333 }, "Pyramids.Policy.Beta.sum": { "value": 0.0004796450149999982, "min": 0.0004796450149999982, "max": 0.13898455647, "count": 333 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00384402833878994, "min": 0.0037226839922368526, "max": 0.6547409296035767, "count": 333 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05381639674305916, "min": 0.05211757495999336, "max": 5.237927436828613, "count": 333 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 187.03821656050957, "min": 163.06989247311827, "max": 999.0, "count": 333 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29365.0, "min": 15884.0, "max": 33758.0, "count": 333 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.8002203718112533, "min": -0.9999806972280625, "max": 1.8370540386116183, "count": 333 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 282.63459837436676, "min": -30.99940161406994, "max": 339.8549971431494, "count": 333 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.8002203718112533, "min": -0.9999806972280625, "max": 1.8370540386116183, "count": 333 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 282.63459837436676, "min": -30.99940161406994, "max": 339.8549971431494, "count": 333 }, "Pyramids.Policy.RndReward.mean": { "value": 0.00748890871219159, "min": 0.006728075081411737, "max": 15.630076319095679, "count": 333 }, "Pyramids.Policy.RndReward.sum": { "value": 1.1757586678140797, "min": 1.1340146101138089, "max": 250.08122110553086, "count": 333 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 333 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 333 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689708856", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/home/arran/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "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": "1689718048" }, "total": 9191.136063812999, "count": 1, "self": 0.21783762199629564, "children": { "run_training.setup": { "total": 0.009290647998568602, "count": 1, "self": 0.009290647998568602 }, "TrainerController.start_learning": { "total": 9190.908935543004, "count": 1, "self": 7.296172509493772, "children": { "TrainerController._reset_env": { "total": 2.2592835880059283, "count": 1, "self": 2.2592835880059283 }, "TrainerController.advance": { "total": 9181.289401419504, "count": 658089, "self": 6.706666782862158, "children": { "env_step": { "total": 5506.038501513656, "count": 658089, "self": 4669.653360345765, "children": { "SubprocessEnvManager._take_step": { "total": 831.8433572594222, "count": 658089, "self": 21.683317840346717, "children": { "TorchPolicy.evaluate": { "total": 810.1600394190755, "count": 625044, "self": 810.1600394190755 } } }, "workers": { "total": 4.54178390846937, "count": 658089, "self": 0.0, "children": { "worker_root": { "total": 9181.73563117189, "count": 658089, "is_parallel": true, "self": 4984.935508643743, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000965316008660011, "count": 1, "is_parallel": true, "self": 0.0002711040433496237, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006942119653103873, "count": 8, "is_parallel": true, "self": 0.0006942119653103873 } } }, "UnityEnvironment.step": { "total": 0.01789177200407721, "count": 1, "is_parallel": true, "self": 0.00021794400527141988, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022436400467995554, "count": 1, "is_parallel": true, "self": 0.00022436400467995554 }, "communicator.exchange": { "total": 0.01678669999819249, "count": 1, "is_parallel": true, "self": 0.01678669999819249 }, "steps_from_proto": { "total": 0.0006627639959333465, "count": 1, "is_parallel": true, "self": 0.00015804098802618682, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005047230079071596, "count": 8, "is_parallel": true, "self": 0.0005047230079071596 } } } } } } }, "UnityEnvironment.step": { "total": 4196.800122528148, "count": 658088, "is_parallel": true, "self": 126.31859621261538, "children": { "UnityEnvironment._generate_step_input": { "total": 91.8040517183108, "count": 658088, "is_parallel": true, "self": 91.8040517183108 }, "communicator.exchange": { "total": 3603.8484257075324, "count": 658088, "is_parallel": true, "self": 3603.8484257075324 }, "steps_from_proto": { "total": 374.82904888968915, "count": 658088, "is_parallel": true, "self": 83.5557382828265, "children": { "_process_rank_one_or_two_observation": { "total": 291.27331060686265, "count": 5264704, "is_parallel": true, "self": 291.27331060686265 } } } } } } } } } } }, "trainer_advance": { "total": 3668.544233122986, "count": 658089, "self": 13.930175016677822, "children": { "process_trajectory": { "total": 710.9470578132459, "count": 658089, "self": 709.6599365632719, "children": { "RLTrainer._checkpoint": { "total": 1.2871212499740068, "count": 20, "self": 1.2871212499740068 } } }, "_update_policy": { "total": 2943.6670002930623, "count": 4716, "self": 1794.112542707604, "children": { "TorchPPOOptimizer.update": { "total": 1149.5544575854583, "count": 227982, "self": 1149.5544575854583 } } } } } } }, "trainer_threads": { "total": 5.110050551593304e-07, "count": 1, "self": 5.110050551593304e-07 }, "TrainerController._save_models": { "total": 0.06407751499500591, "count": 1, "self": 0.001261867000721395, "children": { "RLTrainer._checkpoint": { "total": 0.06281564799428452, "count": 1, "self": 0.06281564799428452 } } } } } } }