102 search results - page 5 / 21 » Efficient Asymptotic Approximation in Temporal Difference Le... |
NIPS
2001
13 years 8 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
NIPS
2008
13 years 8 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...
ATAL
2005
Springer
14 years 29 days ago
2005
Springer
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
JAIR
2006
13 years 7 months ago
2006
In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either e...
UAI
1996
13 years 8 months ago
1996
We discuss Bayesian methods for learning Bayesian networks when data sets are incomplete. In particular, we examine asymptotic approximations for the marginal likelihood of incomp...