ms·1978년 1월 1일
Note—A Note on Dynamic Programming with Unbounded Rewards
J.A.E.E. van Nunen, J. Wessels
Management Science
30
피인용
8.1
FWCI
0
IS/마케팅/OM 탑저널 피인용
8
IS/마케팅/OM 탑저널 참고문헌
- 주제동적계획과 확률최적화 · 생산·최적화
01Abstract
In a recent paper, Lippman presents sufficient conditions for Denardo's N-stage contraction in discounted semi-Markov decision processes with unbounded rewards. In this note it is demonstrated that Lippman's conditions may be replaced by weaker conditions which even imply 1-stage contraction. The verification of the conditions of this note is somewhat easier.
02연구 흐름
불러오는 중…
03비슷한 논문
불러오는 중…
04이후 연구
불러오는 중…
05선행 연구
불러오는 중…
06서지 정보
- 저널Management Science · 24(5) · 576–580
- 토픽Reinforcement Learning in Robotics · Artificial Intelligence
- DOI10.1287/mnsc.24.5.576
- 저자J.A.E.E. van Nunen, J. Wessels