|
Networks of learning automata and limiting games Host Publication: Lecture Notes in Artificial Intelligence Authors: P. Vrancx, K. Verbeeck and A. Nowé Publisher: Springer Verlag Publication Year: 2008 Number of Pages: 15 ISBN: 3-540-77947-7
Abstract: Abstract. 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 a set of decentralized,
independent learning automata is able to control a finite Markov Chain
with unknown transition probabilities and rewards. This result was recently
extended to Markov Games and analyzed with the use of limiting
games. In this paper we continue this analysis but we assume here that
our agents are fully ignorant about the other agents in the environment,
i.e. they can only observe themselves they do not know how many other
agents are present in the environment, the actions these other agents
took, the rewards they received for this, or the location they occupy in
the state space. We prove that in Markov Games, where agents have
this limited type of observability, a network of independent LA is still
able to converge to an equilibrium point of the underlying limiting game,
provided a common ergodic assumption and provided the agents do not
interfere each other's transition probabilities. External Link.
|
