.png){kind=icon}
返回
Regular decision processes
.png){kind=icon}
PRE
AI
DOI：10.1016/j.artint.2024.104113.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We introduce and study Regular Decision Processes (RDPs), a new, compact model for domains with non-Markovian dynamics and rewards, in which the dependence on the past is regular, in the language theoretic sense. RDPs are an intermediate model between MDPs and POMDPs. They generalize k-order MDPs and can be viewed as a POMDP in which the hidden state is a regular function of the entire history. In factored RDPs, transition and reward functions are specified using formulas in linear temporal logics over finite traces, or using regular expressions. This allows specifying complex dependence on the past using intuitive and compact formulas, and building models of partially observable domains without specifying an underlying state space.
Keyword:
Markov-decision processes
Non-Markovian decision processes
POMDPs
Regular languages
期刊
IF:
13.9
论文数:
6.1K
被引数:
1.9W
机构
引用论文
Learning deterministic probabilistic automata from a model checking perspective.png)
MACHINE LEARNING
OAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏分享收藏Physiological control of cholecystokinin release and pancreatic enzyme secretion by intraduodenal bile acids.GutOAAI
GutIF0
OAAI分享收藏Enhanced thermal conductivity and mechanical property through boron nitride hot string in polyvinylidene fluoride fibers by electrospinning通过电纺在聚偏氟乙烯纤维中通过氮化硼热丝增强热导率和机械性能
PREAI
分享收藏Optimal Control of Markov Decision Processes With Linear Temporal Logic Constraints具有线性时序逻辑约束的Markov决策过程的最优控制
PREAI
分享收藏Sticking Together or Falling Apart? : Solidarity in an Era of Individualization and Globalization
OAAI
IF0
OAAI分享收藏
查看更多内容