989 search results - page 22 / 198 » LIME: A System for Learning Relations |
GECCO
2004
Springer
14 years 1 months ago
2004
Springer
This paper introduces a gradient-based reward prediction update mechanism to the XCS classifier system as applied in neuralnetwork type learning and function approximation mechani...
NIPS
2003
13 years 9 months ago
2003
We present a connectionist architecture that can learn a model of the relations between perceptions and actions and use this model for behavior planning. State representations are...
ECAI
2000
Springer
14 years 23 days ago
2000
Springer
Knowledge-based systems (KBS) are not necessarily based on well-defined ontologies. In particular it is possible to build KBS for classification problems, where there is little con...
ICMLA
2003
13 years 9 months ago
2003
This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks th...
COLT
2007
Springer
14 years 2 months ago
2007
Springer
This paper analyzes the potential advantages and theoretical challenges of “active learning” algorithms. Active learning involves sequential sampling procedures that use infor...