55 search results - page 6 / 11 » Approximate Policy Iteration using Large-Margin Classifiers |
CORR
2012
Springer
13 years 5 months ago
2012
Springer
Abstract— In this paper, we consider a class of continuoustime, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation ...
91
Voted
IROS
2007
IEEE
15 years 3 months ago
2007
IEEE
Abstract— We propose to improve the locomotive performance of humanoid robots by using approximated biped stepping and walking dynamics with reinforcement learning (RL). Although...
JMLR
2006
2006
Geometric Variance Reduction in Markov Chains: Application to Value Function and Gradient Estimation
14 years 9 months ago
We study a sequential variance reduction technique for Monte Carlo estimation of functionals in Markov Chains. The method is based on designing sequential control variates using s...
ICMLA
2008
14 years 11 months ago
2008
In reinforcement learning, it is a common practice to map the state(-action) space to a different one using basis functions. This transformation aims to represent the input data i...
ICPR
2006
IEEE
15 years 10 months ago
2006
IEEE
Regeneration of biometric templates from match scores has security and privacy implications related to any biometric based authentication system. In this paper, we propose a novel...