Finite State Control of POMDPs with LTL Specifications

被引：0
作者：
Sharan, Rangoli
Burdick, Joel
机构：
来源：
2014 AMERICAN CONTROL CONFERENCE (ACC) | 2014年
关键词：
AVERAGE COST CRITERION;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
We consider the synthesis of control policies over partially observable Markov decision processes with linear temporal logic specifications. We limit the search of policies over finite state controllers of a fixed size which leads to a Markov chain with free parameters, over which the probability of satisfaction of the specification can be maximized.
引用
收藏
页码：501 / 508
页数：8
相关论文
共 36 条
  • [1] [Anonymous], 1990, HDB THEORETICAL COMP
  • [2] [Anonymous], 1976, Denumerable Markov Chains
  • [3] [Anonymous], THESIS
  • [4] [Anonymous], 2009, MARKOV CHAINS STOCHA
  • [5] [Anonymous], 2008, ROBOTICS SCI SYSTEMS
  • [6] DISCRETE-TIME CONTROLLED MARKOV-PROCESSES WITH AVERAGE COST CRITERION - A SURVEY
    ARAPOSTATHIS, A
    BORKAR, VS
    FERNANDEZGAUCHERAND, E
    GHOSH, MK
    MARCUS, SI
    [J]. SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1993, 31 (02) : 282 - 344
  • [7] OPTIMAL CONTROL OF MARKOV PROCESSES WITH INCOMPLETE STATE INFORMATION
    ASTROM, KJ
    [J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1965, 10 (01) : 174 - &
  • [8] Baier C., 2008, REPRESENTATION MIND
  • [9] BARTLETT PL, 1999, HEBBIAN SYNAPTIC MOD
  • [10] Baxter J., 2001, MACHINES LEARN PLAY, P91
1234