259 search results - page 3 / 52 » Reinforcement Learning with the Use of Costly Features |
ICML
2009
IEEE
14 years 6 months ago
2009
IEEE
The purpose of this paper is three-fold. First, we formalize and study a problem of learning probabilistic concepts in the recently proposed KWIK framework. We give details of an ...
CG
2006
Springer
13 years 7 months ago
2006
Springer
Temporal difference (TD) learning has been used to learn strong evaluation functions in a variety of two-player games. TD-gammon illustrated how the combination of game tree search...
COGSR
2011
13 years 16 days ago
2011
This paper brings together work in modeling episodic memory and reinforcement learning. We demonstrate that is possible to learn to use episodic memory retrievals while simultaneo...
GECCO
2010
Springer
13 years 8 months ago
2010
Springer
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
SGAI
2004
Springer
13 years 11 months ago
2004
Springer
We introduce a new class of Reinforcement Learning algorithms designed to operate in perceptual spaces containing images. They work by classifying the percepts using a computer vi...