arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1405.2652cs.LG
收藏

在强化学习中选择近优近似状态表示

Selecting Near-Optimal Approximate State Representations in Reinforcement Learning

Montanuniversitaet Leoben(莱奥本矿业大学);The Technion(以色列理工学院);Inria Lille-Nord Europe(法国国家信息与自动化研究所里尔-北欧中心);Inria Chile(法国国家信息与自动化研究所智利中心)

Ronald Ortner, Odalric-Ambrym Maillard, Daniil Ryabko

摘要:

我们考虑引入的强化学习设置(Maillard et al.,NIPS 2011),其中学习者没有显式访问底层马尔可夫决策过程(MDP)的状态。相反,她可以访问几个模型,将过去的相互作用历史映射到状态。在这里,我们改进了已知的遗憾界在这种情况下,更重要的是,推广到的情况下,模型给学习者不包含一个真正的模型,导致MDP表示,但只有它的近似值。

英文摘要:

We consider a reinforcement learning setting introduced in (Maillard et al., NIPS 2011) where the learner does not have explicit access to the states of the underlying Markov decision process (MDP). Instead, she has access to several models that map histories of past interactions to states. Here we improve over known regret bounds in this setting, and more importantly generalize to the case where the models given to the learner do not contain a true model resulting in an MDP representation but only approximations of it. We also give improved error bounds for state aggregation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑