86 search results - page 11 / 18 » Evolution of reward functions for reinforcement learning |
ICML
2002
IEEE
16 years 15 days ago
2002
IEEE
We explore dynamic shaping to integrate our prior beliefs of the final policy into a conventional reinforcement learning system. Shaping provides a positive or negative artificial...
CCIA
2005
Springer
15 years 5 months ago
2005
Springer
— This paper proposes a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, whe...
110
click to vote
AAAI
2006
15 years 1 months ago
2006
My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques b...
PKDD
2009
Springer
15 years 6 months ago
2009
Springer
Abstract. The Factored Markov Decision Process (FMDP) framework is a standard representation for sequential decision problems under uncertainty where the state is represented as a ...
IJCNN
2008
IEEE
15 years 6 months ago
2008
IEEE
— In this paper we address the reliability of policies derived by Reinforcement Learning on a limited amount of observations. This can be done in a principled manner by taking in...