{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0261327028274536, "min": 0.7610291838645935, "max": 1.4961549043655396, "count": 7 }, "Pyramids.Policy.Entropy.sum": { "value": 30734.7265625, "min": 22794.345703125, "max": 45387.35546875, "count": 7 }, "Pyramids.Step.mean": { "value": 209929.0, "min": 29952.0, "max": 209929.0, "count": 7 }, "Pyramids.Step.sum": { "value": 209929.0, "min": 29952.0, "max": 209929.0, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.10188606381416321, "min": -0.10188606381416321, "max": -0.06755714118480682, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -24.452655792236328, "min": -24.452655792236328, "max": -16.28127098083496, "count": 7 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02070438116788864, "min": 0.02070438116788864, "max": 0.3795851469039917, "count": 7 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.969051361083984, "min": 4.969051361083984, "max": 89.96167755126953, "count": 7 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06948383712092293, "min": 0.0669552986946384, "max": 0.0718437648804213, "count": 7 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8338060454510752, "min": 0.502906354162949, "max": 0.9147761987872329, "count": 7 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00016674057673984985, "min": 0.00012009727553268412, "max": 0.00663446226275563, "count": 7 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0020008869208781982, "min": 0.0014411673063922095, "max": 0.046441235839289406, "count": 7 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002805339731553444, "min": 0.0002805339731553444, "max": 0.00029838354339596195, "count": 7 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.003366407677864133, "min": 0.0020886848037717336, "max": 0.0037253763582078994, "count": 7 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19351132222222225, "min": 0.19351132222222225, "max": 0.19946118095238097, "count": 7 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.322135866666667, "min": 1.3962282666666668, "max": 2.5417921, "count": 7 }, "Pyramids.Policy.Beta.mean": { "value": 0.009351781089999999, "min": 0.009351781089999999, "max": 0.009946171977142856, "count": 7 }, "Pyramids.Policy.Beta.sum": { "value": 0.11222137307999999, "min": 0.06962320384, "max": 0.12418503079000001, "count": 7 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03376156836748123, "min": 0.03376156836748123, "max": 0.3565838634967804, "count": 7 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.4051388204097748, "min": 0.4051388204097748, "max": 2.496087074279785, "count": 7 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 976.6363636363636, "max": 999.0, "count": 7 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30969.0, "min": 15984.0, "max": 32229.0, "count": 7 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9999355356539449, "min": -1.0000000521540642, "max": -0.8718875516206026, "count": 7 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -30.998001605272293, "min": -31.997201651334763, "max": -16.000000834465027, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9999355356539449, "min": -1.0000000521540642, "max": -0.8718875516206026, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -30.998001605272293, "min": -31.997201651334763, "max": -16.000000834465027, "count": 7 }, "Pyramids.Policy.RndReward.mean": { "value": 0.35670630639839557, "min": 0.35670630639839557, "max": 6.936993133276701, "count": 7 }, "Pyramids.Policy.RndReward.sum": { "value": 11.057895498350263, "min": 11.057895498350263, "max": 110.99189013242722, "count": 7 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716712723", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716713221" }, "total": 497.95184621299995, "count": 1, "self": 0.33572314199955144, "children": { "run_training.setup": { "total": 0.05327586700059328, "count": 1, "self": 0.05327586700059328 }, "TrainerController.start_learning": { "total": 497.5628472039998, "count": 1, "self": 0.42107916293934977, "children": { "TrainerController._reset_env": { "total": 2.2582648210000116, "count": 1, "self": 2.2582648210000116 }, "TrainerController.advance": { "total": 494.69077947705955, "count": 14455, "self": 0.4103215251379879, "children": { "env_step": { "total": 342.7020342810283, "count": 14455, "self": 304.0636459290081, "children": { "SubprocessEnvManager._take_step": { "total": 38.40106151494365, "count": 14455, "self": 1.2628076679593505, "children": { "TorchPolicy.evaluate": { "total": 37.1382538469843, "count": 14434, "self": 37.1382538469843 } } }, "workers": { "total": 0.23732683707657998, "count": 14454, "self": 0.0, "children": { "worker_root": { "total": 496.0590658679739, "count": 14454, "is_parallel": true, "self": 225.6414582790867, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023437170002580388, "count": 1, "is_parallel": true, "self": 0.0006748129990228335, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016689040012352052, "count": 8, "is_parallel": true, "self": 0.0016689040012352052 } } }, "UnityEnvironment.step": { "total": 0.07444514200051344, "count": 1, "is_parallel": true, "self": 0.0006639210005232599, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004881469994870713, "count": 1, "is_parallel": true, "self": 0.0004881469994870713 }, "communicator.exchange": { "total": 0.07153648599978624, "count": 1, "is_parallel": true, "self": 0.07153648599978624 }, "steps_from_proto": { "total": 0.0017565880007168744, "count": 1, "is_parallel": true, "self": 0.00038292299996101065, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013736650007558637, "count": 8, "is_parallel": true, "self": 0.0013736650007558637 } } } } } } }, "UnityEnvironment.step": { "total": 270.4176075888872, "count": 14453, "is_parallel": true, "self": 8.779477905871317, "children": { "UnityEnvironment._generate_step_input": { "total": 6.000877709031556, "count": 14453, "is_parallel": true, "self": 6.000877709031556 }, "communicator.exchange": { "total": 230.4200480139807, "count": 14453, "is_parallel": true, "self": 230.4200480139807 }, "steps_from_proto": { "total": 25.217203960003644, "count": 14453, "is_parallel": true, "self": 5.352794815871675, "children": { "_process_rank_one_or_two_observation": { "total": 19.86440914413197, "count": 115624, "is_parallel": true, "self": 19.86440914413197 } } } } } } } } } } }, "trainer_advance": { "total": 151.57842367089324, "count": 14454, "self": 0.5691707298756228, "children": { "process_trajectory": { "total": 29.43333330902169, "count": 14454, "self": 29.43333330902169 }, "_update_policy": { "total": 121.57591963199593, "count": 82, "self": 70.89063433302454, "children": { "TorchPPOOptimizer.update": { "total": 50.685285298971394, "count": 5295, "self": 50.685285298971394 } } } } } } }, "trainer_threads": { "total": 1.7060001482605003e-06, "count": 1, "self": 1.7060001482605003e-06 }, "TrainerController._save_models": { "total": 0.19272203700074897, "count": 1, "self": 0.0033570360001249355, "children": { "RLTrainer._checkpoint": { "total": 0.18936500100062403, "count": 1, "self": 0.18936500100062403 } } } } } } }