Sciweavers

Share
CORR
2012
Springer
196views Education» more  CORR 2012»
7 years 6 months ago
PAC-Bayesian Policy Evaluation for Reinforcement Learning
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, lar...
Mahdi Milani Fard, Joelle Pineau, Csaba Szepesv&aa...
CORR
2006
Springer
113views Education» more  CORR 2006»
8 years 10 months ago
A Unified View of TD Algorithms; Introducing Full-Gradient TD and Equi-Gradient Descent TD
This paper addresses the issue of policy evaluation in Markov Decision Processes, using linear function approximation. It provides a unified view of algorithms such as TD(), LSTD()...
Manuel Loth, Philippe Preux
ESORICS
2010
Springer
8 years 11 months ago
An Authorization Framework Resilient to Policy Evaluation Failures
Abstract. In distributed computer systems, it is possible that the evaluation of an authorization policy may suffer unexpected failures, perhaps because a sub-policy cannot be eval...
Jason Crampton, Michael Huth
ATAL
2008
Springer
9 years 9 days ago
Sigma point policy iteration
In reinforcement learning, least-squares temporal difference methods (e.g., LSTD and LSPI) are effective, data-efficient techniques for policy evaluation and control with linear v...
Michael H. Bowling, Alborz Geramifard, David Winga...
CCS
2005
ACM
9 years 3 months ago
CPOL: high-performance policy evaluation
Policy enforcement is an integral part of many applications. Policies are often used to control access to sensitive information. Current policy specification languages give users ...
Kevin Borders, Xin Zhao, Atul Prakash
PKDD
2009
Springer
152views Data Mining» more  PKDD 2009»
9 years 4 months ago
Feature Selection for Value Function Approximation Using Bayesian Model Selection
Abstract. Feature selection in reinforcement learning (RL), i.e. choosing basis functions such that useful approximations of the unkown value function can be obtained, is one of th...
Tobias Jung, Peter Stone
ICML
2006
IEEE
9 years 11 months ago
Fast direct policy evaluation using multiscale analysis of Markov diffusion processes
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...
Mauro Maggioni, Sridhar Mahadevan
books