697 search results - page 1 / 140 » New Criteria and a New Algorithm for Learning in Multi-Agent... |
165
click to vote
NIPS
2004
15 years 8 months ago
2004
We propose a new set of criteria for learning algorithms in multi-agent systems, one that is more stringent and (we argue) better justified than previous proposed criteria. Our cr...
178
click to vote
AAAI
2010
15 years 8 months ago
2010
Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting th...
243
Voted
AAMAS
2006
Springer
15 years 7 months ago
2006
Springer
In this paper, we investigate Reinforcement learning (RL) in multi-agent systems (MAS) from an evolutionary dynamical perspective. Typical for a MAS is that the environment is not ...
190
Voted
ATAL
2004
Springer
16 years 13 days ago
2004
Springer
Product Distribution (PD) theory is a new framework for controlling Multi-Agent Systems (MAS’s). First we review one motivation of PD theory, as the information-theoretic extens...
234
click to vote
ATAL
2008
Springer
15 years 9 months ago
2008
Springer
Distributed constraint optimization (DCOP) is a promising approach to coordination, scheduling and task allocation in multi agent networks. In large-scale or low-bandwidth network...