495 search results - page 57 / 99 » Constructing States for Reinforcement Learning |
144
click to vote
JMLR
2008
15 years 4 months ago
2008
Many complex control problems require sophisticated solutions that are not amenable to traditional controller design. Not only is it difficult to model real world systems, but oft...
131
click to vote
AIED
2009
Springer
15 years 10 months ago
2009
Springer
Abstract. While high interactivity has been one of the main characteristics of oneon-one human tutoring, a great deal of controversy surrounds the issue of whether interactivity is...
134
click to vote
JAIR
2011
14 years 11 months ago
2011
Markovian processes have long been used to model stochastic environments. Reinforcement learning has emerged as a framework to solve sequential planning and decision-making proble...
142
click to vote
ECAI
2006
Springer
15 years 7 months ago
2006
Springer
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...
161
click to vote
AGI
2011
14 years 7 months ago
2011
Under Legg’s and Hutter’s formal measure [1], performance in easy environments counts more toward an agent’s intelligence than does performance in difficult environments. An ...