10 search results - page 2 / 2 » An object-oriented representation for efficient reinforcemen... |
105
Voted
UAI
2008
15 years 27 days ago
2008
Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinfor...
ATAL
2008
Springer
15 years 1 months ago
2008
Springer
In reinforcement learning, least-squares temporal difference methods (e.g., LSTD and LSPI) are effective, data-efficient techniques for policy evaluation and control with linear v...
CORR
2010
Springer
14 years 11 months ago
2010
Springer
Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning ...
ICML
2005
IEEE
16 years 9 days ago
2005
IEEE
T ORDER REGRESSION (EXTENDED ABSTRACT) Kurt Driessensa Saso Dzeroskib a Department of Computer Science, University of Waikato, Hamilton, New Zealand (kurtd@waikato.ac.nz) b Departm...
109
click to vote
JIRS
2000
14 years 11 months ago
2000
Agents (hardware or software) that act autonomously in an environment have to be able to integrate three basic behaviors: planning, execution, and learning. This integration is man...