Sciweavers

233 search results - page 31 / 47
» Composing and combining policies under the policy machine
Sort
View
ICML
2005
IEEE
14 years 8 months ago
Proto-value functions: developmental reinforcement learning
This paper presents a novel framework called proto-reinforcement learning (PRL), based on a mathematical model of a proto-value function: these are task-independent basis function...
Sridhar Mahadevan
CSSE
2004
IEEE
13 years 7 months ago
Trustable B2C markets on the semantic web
Abstract. Semantic Web technologies will deeply influence the further development of the Internet Economy. A major challenge is, however, to find a practical solution for trust pro...
Robert Tolksdorf, Christian Bizer, Rainer Eckstein...
RTCSA
2005
IEEE
14 years 1 months ago
Multi-Versions Data for Improvement of QoS in RTDBS
In current research toward the design of more powerful behavior of RTDBS under unpredictable workloads, different research groups focus their work on QoS (Quality of Service) guar...
Emna Bouazizi, Claude Duvallet, Bruno Sadeg
IJCAI
2007
13 years 9 months ago
Bayesian Inverse Reinforcement Learning
Inverse Reinforcement Learning (IRL) is the problem of learning the reward function underlying a Markov Decision Process given the dynamics of the system and the behaviour of an e...
Deepak Ramachandran, Eyal Amir
IJCAI
2003
13 years 8 months ago
Automated Generation of Understandable Contingency Plans
Markov decision processes (MDPs) and contingency planning (CP) are two widely used approaches to planning under uncertainty. MDPs are attractive because the model is extremely gen...
Max Horstmann, Shlomo Zilberstein