340 search results - page 7 / 68 » Kernelized value function approximation for reinforcement le... |
83
Voted
ILP
2003
Springer
15 years 2 months ago
2003
Springer
RRL is a relational reinforcement learning system based on Q-learning in relational state-action spaces. It aims to enable agents to learn how to act in an environment that has no ...
ICMLA
2008
14 years 11 months ago
2008
In reinforcement learning, it is a common practice to map the state(-action) space to a different one using basis functions. This transformation aims to represent the input data i...
NIPS
2008
14 years 11 months ago
2008
In this paper we consider approximate policy-iteration-based reinforcement learning algorithms. In order to implement a flexible function approximation scheme we propose the use o...
144
Voted
Publication
Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schem...
ICML
2001
IEEE
15 years 10 months ago
2001
IEEE
We introduce the first algorithm for off-policy temporal-difference learning that is stable with linear function approximation. Off-policy learning is of interest because it forms...