140 search results - page 11 / 28 » Structural Abstraction Experiments in Reinforcement Learning |
162
click to vote
PKDD
2009
Springer
15 years 8 months ago
2009
Springer
Abstract. This paper focuses on Active Learning with a limited number of queries; in application domains such as Numerical Engineering, the size of the training set might be limite...
132
click to vote
FBIT
2007
IEEE
15 years 10 months ago
2007
IEEE
The paper describes our first experiments on Reinforcement Learning to steer a real robot car. The applied method, Neural Fitted Q Iteration (NFQ) is purely data-driven based on ...
133
click to vote
IROS
2008
IEEE
15 years 10 months ago
2008
IEEE
Abstract. Both self-learning architecture (embedded structure) and explicit/implicit teaching from other agents (environmental design issue) are necessary not only for one behavior...
137
click to vote
ECML
2007
Springer
15 years 10 months ago
2007
Springer
Abstract. Existing relational learning approaches usually work on complete relational data, but real-world data are often incomplete. This paper proposes the MGDA approach to learn...
172
click to vote
JMLR
2010
14 years 10 months ago
2010
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...