Opponent Modelling by Sequence Prediction and Lookahead in Two-Player Games.

Richard Mealing Jonathan L. Shapiro

Published in: ICAISC (2) (2013)

Keyphrases

sequence prediction
two player games
game tree
evaluation function
game playing
monte carlo
imperfect information
search algorithm
markov models
reinforcement learning
decision theory
search tree
tree search
active learning
optimal strategy
state space
structured prediction
temporal difference learning
pairwise