117
Voted
AAAI
1997
15 years 5 months ago
1997
This paper steps back from the standard infinite horizon formulation of reinforcement learning problems to consider the simpler case of finite horizon problems. Although finite ho...
73
Voted
AAAI
1997
15 years 5 months ago
1997
AAAI
1997
15 years 5 months ago
1997
128
Voted
ICMAS
2000
15 years 5 months ago
2000
We present a concept to use off-line learning approaches to achieve on-line learning of cooperative behavior of agents and instantiate this concept for evolutionary learning with ...
159
click to vote
ICMAS
2000
2000
An Experimental Evaluation of Domain-Independent Fault Handling Services in Open Multi-Agent Systems
15 years 5 months ago
A critical challenge to creating effective open multi-agent systems is allowing them to operate effectively in the face of potential failures. In this paper we present an experimen...
131
Voted
ICMAS
2000
15 years 5 months ago
2000
Online auctions are becoming an increasingly important channel for electronic commerce. There exist more than 150 online auction sites on the Internet. It is difficult for users t...
98
Voted
AAAI
1997
15 years 5 months ago
1997
118
Voted
AAAI
1997
15 years 5 months ago
1997
Our goal is to build knowledge acquisition tools that support users in modifying knowledge-based systems. These modi cations may require several individual changes to various comp...
141
Voted
AAAI
1997
15 years 5 months ago
1997
The use of heuristics as a means to improve constraint solver performance has been researched widely. However, most work has been on problem-independentheuristics (e.g., variable ...
108
Voted
AAAI
1997
15 years 5 months ago
1997
We show that a resealed constrainedness parameter provides the basis for accurate numerical models of search cost for both backtracking and local search algorithms. In the past, t...