Acting Optimally in Partially Observable Stochastic Domains

Acting Optimally in Partially Observable Stochastic Domains (1994)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Anthony R. Cassandra , Leslie Pack Kaelbling , Michael L. Littman

Citations:

243 - 16 self

BibTeX

@MISC{Cassandra94actingoptimally,
    author = {Anthony R. Cassandra and Leslie Pack Kaelbling and Michael L. Littman},
    title = {Acting Optimally in Partially Observable Stochastic Domains},
    year = {1994}
}

Bookmark

OpenURL

Abstract

In this paper, we describe the partially observable Markov decision process (pomdp) approach to finding optimal or near-optimal control strategies for partially observable stochastic environments, given a complete model of the environment. The pomdp approach was originally developed in the operations research community and provides a formal basis for planning problems that have been of interest to the AI community. We found the existing algorithms for computing optimal control strategies to be highly computationally inefficient and have developed a new algorithm that is empirically more efficient. We sketch this algorithm and present preliminary results on several small problems that illustrate important properties of the pomdp approach.

Citations

1964	Dynamic Programming - Bellman - 1957
434	Dynamic programming and Markov processes - Howard - 1960
427	Integrated architectures for learning, planning, and reacting based on approximating integrated architectures for learning, planning, and reacting based on approximating dynamic programming - Sutton - 1990
293	A formal theory of knowledge and action - Moore - 1985
285	The Optimal Control of Partially Observable Markov Processes - Sondik - 1971
253	The complexity of Markov decision processes - Papadimitriou, Tsisiklis - 1987
235	The optimal control of partially observable Markov processes over a finite horizon - Smallwood, Sondik - 1973
173	Reinforcement learning with perceptual aliasing: The perceptual distinctions approach - Chrisman - 1992
165	Survey of partially observable markov decision processes: Theory, models, and algorithms - Monahan - 1982
151	A survey of algorithmic methods for partially observed Markov decision processes - Lovejoy - 1991
125	Planning with deadlines in stochastic domains - Dean, Kaelbling, et al. - 1993
105	Realtime learning and control using asynchronous dynamic programmming - Baro, Bradtke, et al. - 1991
99	Optimal control of Markov decision processes with incomplete state estimation - Astrom - 1965
96	Overcoming incomplete perception with utile distinction memory - McCallum - 1993
69	Algorithms for partially observable Markov decision processes. Doctoral dissertation - Cheng - 1988
12	Cost-sensitive reinforcement learning for adaptive classification and control - Tan - 1991
7	Algorithms for partially observable markov decision processes - Cassandra, Kaelbling, et al. - 1994