86 search results - page 11 / 18 » Evolution of reward functions for reinforcement learning |
139
click to vote
ICML
2002
IEEE
16 years 6 months 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...
160
click to vote
CCIA
2005
Springer
15 years 11 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...
179
click to vote
AAAI
2006
15 years 7 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...
159
click to vote
PKDD
2009
Springer
16 years 17 days 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 ...
136
click to vote
IJCNN
2008
IEEE
16 years 13 days 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...