"Horizon"的相关文档

Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning
TighteningtheDependenceonHorizonintheSampleComplexityofQ-LearningGenLi1ChangxiaoCai2YuxinChen2YuantaoGu1YutingWei3YuejieChi4AbstractQ-learning(Borkar&Meyn,2000;Jaakkolaetal.,1994;Szepesva´ri,1998;...
on the in Sample Dependence
2023-11-16 19:42:081037390.16 KB21
下载文档
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
UnderstandingtheCurseofHorizoninOff-PolicyEvaluationviaConditionalImportanceSamplingYaoLiu1Pierre-LucBacon2EmmaBrunskill1Abstractincreasinginterestindevelopingaccurateandefﬁcientalgo-rithmsforoff-...
of the in Off-Policy Understanding
2023-11-14 21:46:541892287.9 KB23
下载文档
Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning
MaximumEntropyGainExplorationforLongHorizonMulti-goalReinforcementLearningSilviuPitis12HarrisChan12StephenZhao1BradlyStadie2JimmyBa12AbstractInthispaper,weimproveuponexistingapproachestointrin-sicg...
for Exploration Maximum Entropy GAIN
2023-11-14 21:45:0814473.6 MB18
下载文档