arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1202.3699cs.AI
收藏

学习即规划:基于蒙特卡罗树搜索的近贝叶斯最优强化学习

Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search

Rutgers University(罗格斯大学)

John Asmuth, Michael L. Littman

摘要:

贝叶斯最优行为虽然定义明确,但往往难以实现。蒙特卡罗树搜索(MCTS)的最新进展表明,它是可能的行动接近最佳的马尔可夫决策过程(MDP)非常大或无限的状态空间。未知MDP中的贝叶斯最优行为等同于已知置信空间MDP中的最优行为,尽管该置信空间MDP的大小随着所保留的历史量呈指数增长,并且可能是无限的。我们展示了一个代理如何使用一个特定的MCTS算法,前向搜索稀疏采样(FSSS),在一个有效的方式采取行动几乎贝叶斯最优的所有步骤,但多项式数量,假设FSSS可以用来有效地采取行动,在任何可能的底层MDP。

英文摘要:

Bayes-optimal behavior, while well-defined, is often difficult to achieve. Recent advances in the use of Monte-Carlo tree search (MCTS) have shown that it is possible to act near-optimally in Markov Decision Processes (MDPs) with very large or infinite state spaces. Bayes-optimal behavior in an unknown MDP is equivalent to optimal behavior in the known belief-space MDP, although the size of this belief-space MDP grows exponentially with the amount of history retained, and is potentially infinite. We show how an agent can use one particular MCTS algorithm, Forward Search Sparse Sampling (FSSS), in an efficient way to act nearly Bayes-optimally for all but a polynomial number of steps, assuming that FSSS can be used to act efficiently in any possible underlying MDP.

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。

↑