{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1480385959148407, "min": 0.12577205896377563, "max": 1.407615303993225, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4455.36962890625, "min": 3738.95166015625, "max": 42701.41796875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999958.0, "min": 29909.0, "max": 2999958.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999958.0, "min": 29909.0, "max": 2999958.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8194014430046082, "min": -0.11869058012962341, "max": 0.8890250325202942, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 249.9174346923828, "min": -28.48573875427246, "max": 270.4315185546875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04218282178044319, "min": -0.015763267874717712, "max": 0.3245433270931244, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.865760803222656, "min": -4.387302398681641, "max": 76.9167709350586, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07132229140205754, "min": 0.06464629629992096, "max": 0.07585698586041746, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9985120796288055, "min": 0.5046457076509115, "max": 1.1074906732925835, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016802089877143902, "min": 0.0001684285054546628, "max": 0.01683753949162555, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23522925828001462, "min": 0.0020211420654559537, "max": 0.2357255528827577, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.542770914347618e-06, "min": 1.542770914347618e-06, "max": 0.00029841158624375715, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1598792800866652e-05, "min": 2.1598792800866652e-05, "max": 0.0036456578847807323, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051422380952381, "min": 0.10051422380952381, "max": 0.1994705285714286, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071991333333334, "min": 1.3962937000000002, "max": 2.6475447000000005, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.137095857142854e-05, "min": 6.137095857142854e-05, "max": 0.009947105804285714, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008591934199999996, "min": 0.0008591934199999996, "max": 0.12153040474, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007724138908088207, "min": 0.0075074173510074615, "max": 0.4261355996131897, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10813794285058975, "min": 0.10510384291410446, "max": 2.9829492568969727, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 230.87121212121212, "min": 208.64084507042253, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30475.0, "min": 16708.0, "max": 33393.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.737593877861518, "min": -0.9998903740798274, "max": 1.7899929469739888, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 227.62479799985886, "min": -30.996601596474648, "max": 254.1789984703064, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.737593877861518, "min": -0.9998903740798274, "max": 1.7899929469739888, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 227.62479799985886, "min": -30.996601596474648, "max": 254.1789984703064, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018510345994157275, "min": 0.017354215947130575, "max": 7.546017362790949, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.424855325234603, "min": 2.30379801626259, "max": 128.28229516744614, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1752863566", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752873641" }, "total": 10074.616788535, "count": 1, "self": 0.5870842530002847, "children": { "run_training.setup": { "total": 0.04048683700057154, "count": 1, "self": 0.04048683700057154 }, "TrainerController.start_learning": { "total": 10073.989217445, "count": 1, "self": 6.534379731918307, "children": { "TrainerController._reset_env": { "total": 5.390728317999674, "count": 1, "self": 5.390728317999674 }, "TrainerController.advance": { "total": 10061.988250691082, "count": 194877, "self": 7.185497422322442, "children": { "env_step": { "total": 7051.888903804124, "count": 194877, "self": 6593.858947061981, "children": { "SubprocessEnvManager._take_step": { "total": 453.919920646902, "count": 194877, "self": 19.34705994095475, "children": { "TorchPolicy.evaluate": { "total": 434.5728607059473, "count": 187559, "self": 434.5728607059473 } } }, "workers": { "total": 4.110036095241412, "count": 194877, "self": 0.0, "children": { "worker_root": { "total": 10047.693342537867, "count": 194877, "is_parallel": true, "self": 3966.0790257844455, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004424286999892502, "count": 1, "is_parallel": true, "self": 0.0015369630009445245, "children": { "_process_rank_one_or_two_observation": { "total": 0.002887323998947977, "count": 8, "is_parallel": true, "self": 0.002887323998947977 } } }, "UnityEnvironment.step": { "total": 0.07288863600024342, "count": 1, "is_parallel": true, "self": 0.000666165000438923, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005296879999150406, "count": 1, "is_parallel": true, "self": 0.0005296879999150406 }, "communicator.exchange": { "total": 0.06914030400002957, "count": 1, "is_parallel": true, "self": 0.06914030400002957 }, "steps_from_proto": { "total": 0.0025524789998598862, "count": 1, "is_parallel": true, "self": 0.0005178189976504655, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020346600022094208, "count": 8, "is_parallel": true, "self": 0.0020346600022094208 } } } } } } }, "UnityEnvironment.step": { "total": 6081.614316753421, "count": 194876, "is_parallel": true, "self": 132.36248300717398, "children": { "UnityEnvironment._generate_step_input": { "total": 89.4450760909458, "count": 194876, "is_parallel": true, "self": 89.4450760909458 }, "communicator.exchange": { "total": 5478.473773206933, "count": 194876, "is_parallel": true, "self": 5478.473773206933 }, "steps_from_proto": { "total": 381.3329844483678, "count": 194876, "is_parallel": true, "self": 83.2534491589222, "children": { "_process_rank_one_or_two_observation": { "total": 298.07953528944563, "count": 1559008, "is_parallel": true, "self": 298.07953528944563 } } } } } } } } } } }, "trainer_advance": { "total": 3002.913849464635, "count": 194877, "self": 13.11643810948226, "children": { "process_trajectory": { "total": 477.46207608722943, "count": 194877, "self": 476.77965212623167, "children": { "RLTrainer._checkpoint": { "total": 0.6824239609977667, "count": 6, "self": 0.6824239609977667 } } }, "_update_policy": { "total": 2512.3353352679233, "count": 1388, "self": 1015.8931870820015, "children": { "TorchPPOOptimizer.update": { "total": 1496.4421481859217, "count": 68379, "self": 1496.4421481859217 } } } } } } }, "trainer_threads": { "total": 1.0780004231492057e-06, "count": 1, "self": 1.0780004231492057e-06 }, "TrainerController._save_models": { "total": 0.0758576259995607, "count": 1, "self": 0.002308154998900136, "children": { "RLTrainer._checkpoint": { "total": 0.07354947100066056, "count": 1, "self": 0.07354947100066056 } } } } } } }