Sciweavers

16 search results - page 2 / 4
» Rationality of Reward Sharing in Multi-agent Reinforcement L...
Sort
View
AGENTS
1999
Springer
13 years 9 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 8 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 5 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 6 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
13 years 11 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