567 search results - page 3 / 114 » Regularized Policy Iteration |
AUTOMATICA
2004
13 years 4 months ago
2004
This paper formulates an unconstrained optimal policy for control of regular languages realized as deterministic
NIPS
2003
13 years 6 months ago
2003
We describe a new approximation algorithm for solving partially observable MDPs. Our bounded policy iteration approach searches through the space of bounded-size, stochastic fini...
JMLR
2006
2006
Geometric Variance Reduction in Markov Chains: Application to Value Function and Gradient Estimation
13 years 4 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...
AUTOMATICA
2008
13 years 5 months ago
2008
It is well known that stochastic control systems can be viewed as Markov decision processes (MDPs) with continuous state spaces. In this paper, we propose to apply the policy iter...
Publication
Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schem...