95 search results - page 1 / 19 » Reduction Techniques for Instance-Based Learning Algorithms |
ML
2000
ACM
13 years 10 months ago
2000
ACM
ICML
2003
IEEE
14 years 11 months ago
2003
IEEE
Relational reinforcement learning (RRL) is a Q-learning technique which uses first order regression techniques to generalize the Qfunction. Both the relational setting and the Q-l...
ROBOCUP
2007
Springer
14 years 5 months ago
2007
Springer
Abstract. Two main challenges of robot action planning in real domains are uncertain action effects and dynamic environments. In this paper, an instance-based action model is lear...
ICML
2001
IEEE
14 years 11 months ago
2001
IEEE
This paper addresses the issue of reducing the storage requirements on Instance-Based Learning algorithms. Algorithms proposed by other researches use heuristics to prune instance...
NIPS
2001
14 years 8 days ago
2001
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...