Sciweavers

4 search results - page 1 / 1
» All learning is Local: Multi-agent Learning in Global Reward...
Sort
View
NIPS
2003
13 years 5 months ago
All learning is Local: Multi-agent Learning in Global Reward Games
In large multiagent games, partial observability, coordination, and credit assignment persistently plague attempts to design good learning algorithms. We provide a simple and efï¬...
Yu-Han Chang, Tracey Ho, Leslie Pack Kaelbling
HIS
2004
13 years 6 months ago
Stigmergy in Multi Agent Reinforcement Learning
In this paper, we describe how certain aspects of the biological phenomena of stigmergy can be imported into multiagent reinforcement learning (MARL), with the purpose of better e...
Raghav Aras, Alain Dutech, François Charpil...
ICML
2003
IEEE
14 years 5 months ago
Q-Decomposition for Reinforcement Learning Agents
The paper explores a very simple agent design method called Q-decomposition, wherein a complex agent is built from simpler subagents. Each subagent has its own reward function and...
Stuart J. Russell, Andrew Zimdars
ICML
1999
IEEE
14 years 5 months ago
Distributed Value Functions
Many interesting problems, such as power grids, network switches, and tra c ow, that are candidates for solving with reinforcement learningRL, alsohave properties that make distri...
Jeff G. Schneider, Weng-Keen Wong, Andrew W. Moore...