82 search results - page 4 / 17 » MDPs: Learning in Varying Environments |
ICML
2003
IEEE
14 years 10 months ago
2003
IEEE
We investigate methods for planning in a Markov Decision Process where the cost function is chosen by an adversary after we fix our policy. As a running example, we consider a rob...
JMLR
2008
13 years 9 months ago
2008
In this paper we develop a theoretical analysis of the performance of sampling-based fitted value iteration (FVI) to solve infinite state-space, discounted-reward Markovian decisi...
AMAI
2004
Springer
14 years 3 months ago
2004
Springer
This work introduces a new query inference model that can access data and communicate with a teacher by asking finitely many boolean queries in a language L. In this model the pa...
IADIS
2003
13 years 11 months ago
2003
In order to understand and enhance the value of new media in education it is necessary to develop criteria for the evaluation of the effectiveness of learning with hypermedia envi...
ICPR
2008
IEEE
14 years 11 months ago
2008
IEEE
We outline an incremental learning algorithm designed for nonstationary environments where the underlying data distribution changes over time. With each dataset drawn from a new e...