NN
2010
Springer
13 years 7 months ago
2010
Springer
Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...
CDC
2010
IEEE
13 years 7 months ago
2010
IEEE
We consider the classical finite-state discounted Markovian decision problem, and we introduce a new policy iteration-like algorithm for finding the optimal state costs or Q-facto...
CDC
2010
IEEE
13 years 7 months ago
2010
IEEE
Approximate policy iteration methods based on temporal differences are popular in practice, and have been tested extensively, dating to the early nineties, but the associated conve...
AUTOMATICA
2008
14 years 26 days 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...
NIPS
2003
14 years 2 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...
NIPS
2001
14 years 2 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. ...
AAAI
2006
14 years 2 months ago
2006
We present a new algorithm, called incremental least squares policy iteration (ILSPI), for finding the infinite-horizon stationary policy for partially observable Markov decision ...
UAI
2008
14 years 2 months ago
2008
Bounded policy iteration is an approach to solving infinitehorizon POMDPs that represents policies as stochastic finitestate controllers and iteratively improves a controller by a...
AAAI
2007
14 years 3 months ago
2007
We describe a point-based policy iteration (PBPI) algorithm for infinite-horizon POMDPs. PBPI replaces the exact policy improvement step of Hansen’s policy iteration with point...
VALUETOOLS
2006
ACM
14 years 6 months ago
2006
ACM
Min-max functions are dynamic programming operators of zero-sum deterministic games with finite state and action spaces. The problem of computing the linear growth rate of the or...