Sciweavers

1400 search results - page 172 / 280
» Dynamic Galois Theory
Sort
View
AAAI
2006
15 years 21 days ago
Value-Function-Based Transfer for Reinforcement Learning Using Structure Mapping
Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a ps...
Yaxin Liu, Peter Stone
FLAIRS
2001
15 years 20 days ago
Improving Knowledge-Based System Performance by Reordering Rule Sequences
In this paper, we argue that KBS validation should not be limited to testing functional properties of the system, such as its input - output behavior, but must also address its dy...
Neli Zlatareva
EFDBS
2003
15 years 20 days ago
Implementing Mediators through Virtual Updateable Views
Mediators are considered basic architectural units for integration of distributed, heterogeneous information resources. In the paper we propose powerful virtual updateable views as...
Hanna Kozankiewicz, Jacek Leszczylowski, Kazimierz...
NIPS
2001
15 years 20 days ago
The Steering Approach for Multi-Criteria Reinforcement Learning
We consider the problem of learning to attain multiple goals in a dynamic environment, which is initially unknown. In addition, the environment may contain arbitrarily varying ele...
Shie Mannor, Nahum Shimkin
FLAIRS
2000
15 years 19 days ago
Domain Semantics for Agent-Oriented Programming
This paper describes a novel semantic framework for an agent architecture. Drawing on Shoham's work on AGENT0 (Shoham 1993), we replace Shoham's modal logic semantics wi...
Roger Norton, S. Rebecca Thomas