Sciweavers

1234 search results - page 181 / 247
» Multi-criteria Reinforcement Learning
Sort
View
AIPS
2008
14 years 16 days ago
Learning Heuristic Functions through Approximate Linear Programming
Planning problems are often formulated as heuristic search. The choice of the heuristic function plays a significant role in the performance of planning systems, but a good heuris...
Marek Petrik, Shlomo Zilberstein
AAAI
2010
13 years 11 months ago
Multi-Agent Learning with Policy Prediction
Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting th...
Chongjie Zhang, Victor R. Lesser
NIPS
2008
13 years 11 months ago
Temporal Difference Based Actor Critic Learning - Convergence and Neural Implementation
Actor-critic algorithms for reinforcement learning are achieving renewed popularity due to their good convergence properties in situations where other approaches often fail (e.g.,...
Dotan Di Castro, Dmitry Volkinshtein, Ron Meir
ICGA
2008
100views Optimization» more  ICGA 2008»
13 years 10 months ago
Learning the Piece Values for Three Chess Variants
A set of experiments for learning the values of chess pieces is described for the popular chess variants Crazyhouse Chess, Suicide Chess, and Atomic Chess. We follow an establishe...
Sacha Droste, Johannes Fürnkranz
ECAI
2006
Springer
14 years 1 months ago
Using Emotions for Behaviour-Selection Learning
Emotions play a very important role in human behaviour and social interaction. In this paper we present a control architecture which uses emotions in the behaviour selection proces...
Maria Malfaz, Miguel Angel Salichs