949 search results - page 60 / 190 » Can Doxastic Agents Learn |
89
Voted
AAAI
2008
15 years 3 months ago
2008
We propose an opponent modeling approach for no-limit Texas hold-em poker that starts from a (learned) prior, i.e., general expectations about opponent behavior and learns a relat...
98
Voted
ECML
2007
Springer
15 years 7 months ago
2007
Springer
Imitation-based learning is a general mechanism for rapid acquisition of new behaviors in autonomous agents and robots. In this paper, we propose a new approach to learning by imit...
111
click to vote
AAAI
1993
15 years 2 months ago
1993
learning (EBL) component. In this paper we provide a brief review of FOIL and FOCL, then discuss how operationalizing a domain theory can adversely affect the accuracy of a learned...
108
Voted
LAMAS
2005
Springer
15 years 6 months ago
2005
Springer
We present a new multiagent learning algorithm, RVσ(t), that builds on an earlier version, ReDVaLeR . ReDVaLeR could guarantee (a) convergence to best response against stationary ...
108
Voted
GECCO
2008
Springer
15 years 1 months ago
2008
Springer
A developmental model of neural network is presented and evaluated in the game of Checkers. The network is developed using cartesian genetic programs (CGP) as genotypes. Two agent...