An improved policy iteration algorithm for partially observable MDPs

Advances in Neural Information Processing Systems

Volumn , Issue , 1998, Pages 1015-1021

  Hansen, Eric A ^a  

^a Biologically Inspired Neural and Dynamical Systems Laboratory   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; CONTROLLERS;

DECISION PROCESS; FINITE-STATE CONTROLLERS; INFINITE HORIZONS; POLICY EVALUATION; POLICY ITERATION ALGORITHMS; VALUE ITERATION;

ITERATIVE METHODS;

EID: 84898987770     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. Blackwell, D. (1965) Discounted dynamic programming. Ann. Math. Stat. 36:226- 235.
2. Cassandra, A.; Kaelbling, L.P.; Littman, M.L. (1994) Acting optimally in partially observable stochastic domains. In Proc. 13th National Conf. on AI, 1023-1028.
3. Cassandra, A.; Littman, M.L.; & Zhang, N.L. (1997) Incremental pruning: A simple, fast, exact algorithm for partially observable Markov decision processes. In Proc. 13th Annual Conf. on Uncertainty in AL.
4. Hansen, E.A. (1998). Finite-Memory Control of Partially Observable Systems. PhD thesis, Department of Computer Science, University of Massachusetts at Amherst.
5. Jaakkola, T.; Singh, S.P.; &: Jordan, M.I. (1995) Reinforcement learning algorithm for partially observable Markov decision problems. In NIPS-7.
6. Littman, M.L.; Cassandra, A.R.; &: Kaebling, L.P. (1995) Efficient dynamic- programming updates in partially observable Markov decision processes. Computer Science Technical Report CS-95-19, Brown University.
7. Monahan, G.E. (1982) A survey of partially observable Markov decision processes: Theory, models, and algorithms. Management Science 28:1-16.
8. Small wood, R.D. & Sondik, E.J. (1973) The optimal control of partially observable Markov processes over a finite horizon. Operations Research 21:1071-1088.
9. Sondik, E.J. (1971) The Optimal Control of Partially Observable Markov Processes. PhD thesis, Department of Electrical Engineering, Stanford University.
10. Sondik, E.J. (1978) The optimal control of partially observable Markov processes over the infinite horizon: Discounted costs. Operations Research 26:282-304.