Computer Science – Systems and Control
Scientific paper
2011-07-25
Computer Science
Systems and Control
28 pages, 11 figures, submitted to IEEE TAC
Scientific paper
This paper handles a kind of strategic game called potential games and develops a novel learning algorithm Payoff-based Inhomogeneous Partially Irrational Play (PIPIP). The present algorithm is based on Distributed Inhomogeneous Synchronous Learning (DISL) presented in an existing work but, unlike DISL,PIPIP allows agents to make irrational decisions with a specified probability, i.e. agents can choose an action with a low utility from the past actions stored in the memory. Due to the irrational decisions, we can prove convergence in probability of collective actions to potential function maximizers. Finally, we demonstrate the effectiveness of the present algorithm through experiments on a sensor coverage problem. It is revealed through the demonstration that the present learning algorithm successfully leads agents to around potential function maximizers even in the presence of undesirable Nash equilibria. We also see through the experiment with a moving density function that PIPIP has adaptability to environmental changes.
Fujita Masayuki
Goto Tatsuhiko
Hatanaka Takeshi
No associations
LandOfFree
Payoff-based Inhomogeneous Partially Irrational Play for Potential Game Theoretic Cooperative Control of Multi-agent Systems does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Payoff-based Inhomogeneous Partially Irrational Play for Potential Game Theoretic Cooperative Control of Multi-agent Systems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Payoff-based Inhomogeneous Partially Irrational Play for Potential Game Theoretic Cooperative Control of Multi-agent Systems will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-571923