9841 search results - page 286 / 1969 » Distributed Value Functions |
171
click to vote
ICML
2001
IEEE
16 years 7 months ago
2001
IEEE
This paper examines the notion of symmetry in Markov decision processes (MDPs). We define symmetry for an MDP and show how it can be exploited for more effective learning in singl...
169
click to vote
ICML
1998
IEEE
16 years 7 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...
164
click to vote
ATAL
2005
Springer
16 years 23 hour ago
2005
Springer
Temporal difference (TD) learning methods [22] have become popular reinforcement learning techniques in recent years. TD methods have had some experimental successes and have been...
144
click to vote
STOC
2000
ACM
15 years 10 months ago
2000
ACM
We consider a new model for computing with uncertainty. It is desired to compute a function f X1; : : : ; Xn where X1; : : : ; Xn are unknown, but guaranteed to lie in speci ed i...
206
click to vote
HIM
1997
Springer
15 years 10 months ago
1997
Springer
Classical retrieval models support content-oriented searching for documents using a set of words as data model. However, in hypertext and database applications we want to consider...