arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1002.1480cs.AIcs.LGcs.RO
收藏

非折扣马尔可夫决策过程的最小相对熵控制器

A Minimum Relative Entropy Controller for Undiscounted Markov Decision Processes

University of Cambridge(剑桥大学)

Pedro A. Ortega, Daniel A. Braun

摘要:

自适应控制问题是出了名的难以解决,即使在工厂特定的控制器的存在。绕过最优策略的棘手计算的一种方法是将自适应控制重述为忽略来自通知控制器的真实工厂动态的控制器的相对熵的最小化。解决方案是由贝叶斯控制规则-一组方程表征一类可能的植物动态的随机自适应控制器。在这里,贝叶斯控制规则被应用到推导BCR-MDP,一个控制器来解决有限的状态和动作空间和未知动态的非折扣马尔可夫决策过程。特别是,我们推导出一个非参数共轭先验分布的政策空间,封装代理的整个相关的历史,我们提出了一个吉布斯采样器,从这个分布随机政策。初步结果表明,BCR-MDP成功地避免了次优极限环,由于其内置的机制,以平衡勘探与开发。

英文摘要:

Adaptive control problems are notoriously difficult to solve even in the presence of plant-specific controllers. One way to by-pass the intractable computation of the optimal policy is to restate the adaptive control as the minimization of the relative entropy of a controller that ignores the true plant dynamics from an informed controller. The solution is given by the Bayesian control rule-a set of equations characterizing a stochastic adaptive controller for the class of possible plant dynamics. Here, the Bayesian control rule is applied to derive BCR-MDP, a controller to solve undiscounted Markov decision processes with finite state and action spaces and unknown dynamics. In particular, we derive a non-parametric conjugate prior distribution over the policy space that encapsulates the agent's whole relevant history and we present a Gibbs sampler to draw random policies from this distribution. Preliminary results show that BCR-MDP successfully avoids sub-optimal limit cycles due to its built-in mechanism to balance exploration versus exploitation.

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。

↑