135 search results - page 20 / 27 » Using Reinforcement Learning to Coordinate Better |
ACL
2010
14 years 7 months ago
2010
We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to unde...
GECCO
2009
Springer
15 years 4 months ago
2009
Springer
Tetris is a falling block game where the player’s objective is to arrange a sequence of different shaped tetrominoes smoothly in order to survive. In the intelligence games, ag...
82
Voted
ACL
2010
14 years 7 months ago
2010
Current turn-taking approaches for spoken dialogue systems rely on the speaker releasing the turn before the other can take it. This reliance results in restricted interactions th...
ROBOCUP
2000
Springer
15 years 1 months ago
2000
Springer
Q-learning, a most widely used reinforcement learning method, normally needs well-defined quantized state and action spaces to converge. This makes it difficult to be applied to re...
ICML
2009
IEEE
15 years 10 months ago
2009
IEEE
In this paper we introduce the first algorithms for efficiently learning a simulation policy for Monte-Carlo search. Our main idea is to optimise the balance of a simulation polic...