168 search results - page 8 / 34 » Optimism in Reinforcement Learning Based on Kullback-Leibler... |
158
click to vote
ICML
1998
IEEE
16 years 6 months ago
1998
IEEE
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
154
click to vote
AAAI
2010
15 years 7 months ago
2010
This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian...
134
click to vote
FLAIRS
1998
15 years 7 months ago
1998
Manyindustrial processes involve makingparts with an assemblyof machines, where each machinecarries out an operation on a part, and the finished product requires a wholeseries of ...
146
click to vote
ICML
2003
IEEE
16 years 6 months ago
2003
IEEE
We consider incorporating action elimination procedures in reinforcement learning algorithms. We suggest a framework that is based on learning an upper and a lower estimates of th...
168
click to vote
ECML
2006
Springer
15 years 9 months ago
2006
Springer
Reinforcement learning in real-world domains suffers from three curses of dimensionality: explosions in state and action spaces, and high stochasticity. We present approaches that ...