A Reinforcement Learning Scheme for a Partially-Observable Multi-Agent Game.

A Reinforcement Learning Scheme for a Partially-Observable Multi-Agent Game.

We formulate an automatic strategy acquisition problem for the multi-agent card game "Hearts" as a reinforcement learning problem. The problem can approximately be dealt with in the framework of a partially observable Markov decision process (POMDP) for a single-agent system. Hearts is an...

Disgrifiad llawn

Manylion Llyfryddiaeth
Cyhoeddwyd yn:Machine learning. 59, 1-2 (2005).
Prif Awdur: Ishii, Shin
Fformat: Erthygl
Iaith:English
Pynciau:
Reinforcement learning.
POMDP.
Multi-agent system.
Card game.
Model-based.