236 search results - page 16 / 48 » Bias and Variance Approximation in Value Function Estimates |
ESANN
2004
13 years 10 months ago
2004
Several reinforcement-learning techniques have already been applied to the Acrobot control problem, using linear function approximators to estimate the value function. In this pape...
ML
1998
ACM
13 years 8 months ago
1998
ACM
It is well known that prior knowledge or bias can speed up learning, at least in theory. It has proved di cult to make constructive use of prior knowledge, so that approximately c...
ATAL
2005
Springer
14 years 2 months 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...
WEBDB
2004
Springer
14 years 2 months ago
2004
Springer
Current approaches for answering queries with imprecise constraints require users to provide distance metrics and importance measures for attributes of interest. In this paper we ...
RSS
2007
13 years 10 months ago
2007
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...