TY - CHAP
T1 - Hidden-Mode Markov Decision Processes for Nonstationary Sequential Decision Making
AU - Choi, Samuel P.M.
AU - Yeung, Dit Yan
AU - Zhang, Nevin L.
N1 - Publisher Copyright:
© Springer-Verlag Berlin Heidelberg 2000.
PY - 2001
Y1 - 2001
N2 - Problem formulation is often an important first step for solving a problem effectively. In sequential decision problems, Markov decision process (MDP) ([2]; [22]) is a model formulation that has been commonly used, due to its generality, flexibility, and applicability to a wide range of problems. Despite these advantages, there are three necessary conditions that must be satisfied before the MDP model can be applied; that is, 1. The environment model is given in advance (a completely-known environment). 2. The environment states are completely observable (fully-observable states, implying a Markovian environment). 3. The environment parameters do not change over time (a stationary environment).
AB - Problem formulation is often an important first step for solving a problem effectively. In sequential decision problems, Markov decision process (MDP) ([2]; [22]) is a model formulation that has been commonly used, due to its generality, flexibility, and applicability to a wide range of problems. Despite these advantages, there are three necessary conditions that must be satisfied before the MDP model can be applied; that is, 1. The environment model is given in advance (a completely-known environment). 2. The environment states are completely observable (fully-observable states, implying a Markovian environment). 3. The environment parameters do not change over time (a stationary environment).
KW - Markov Decision Process
KW - Neural Information Processing System
KW - Partially Observable Markov Decision Process
KW - Reward Function
KW - State Transition Probability
UR - https://www.scopus.com/pages/publications/105045574527
U2 - 10.1007/3-540-44565-X_12
DO - 10.1007/3-540-44565-X_12
M3 - Chapter
AN - SCOPUS:105045574527
T3 - Lecture Notes in Computer Science
SP - 264
EP - 287
BT - Lecture Notes in Computer Science
ER -