Sciweavers

16 search results - page 2 / 4
» Rationality of Reward Sharing in Multi-agent Reinforcement L...
Sort
View
AGENTS
1999
Springer
13 years 11 months ago
General Principles of Learning-Based Multi-Agent Systems
We consider the problem of how to design large decentralized multiagent systems (MAS’s) in an automated fashion, with little or no hand-tuning. Our approach has each agent run a...
David Wolpert, Kevin R. Wheeler, Kagan Tumer
ICML
1994
IEEE
13 years 11 months ago
Markov Games as a Framework for Multi-Agent Reinforcement Learning
In the Markov decision process (MDP) formalization of reinforcement learning, a single adaptive agent interacts with an environment defined by a probabilistic transition function....
Michael L. Littman
TSMC
2008
146views more  TSMC 2008»
13 years 7 months ago
Decentralized Learning in Markov Games
Learning Automata (LA) were recently shown to be valuable tools for designing Multi-Agent Reinforcement Learning algorithms. One of the principal contributions of LA theory is tha...
Peter Vrancx, Katja Verbeeck, Ann Nowé
ICONIP
2007
13 years 9 months ago
Finding Exploratory Rewards by Embodied Evolution and Constrained Reinforcement Learning in the Cyber Rodents
The aim of the Cyber Rodent project [1] is to elucidate the origin of our reward and affective systems by building artificial agents that share the natural biological constraints...
Eiji Uchibe, Kenji Doya
AAMAS
2007
Springer
14 years 1 months ago
Networks of Learning Automata and Limiting Games
Learning Automata (LA) were recently shown to be valuable tools for designing Multi-Agent Reinforcement Learning algorithms. One of the principal contributions of LA theory is that...
Peter Vrancx, Katja Verbeeck, Ann Nowé