zbMATH — the first resource for mathematics

Socially-aware multiagent learning: towards socially optimal outcomes. (English) Zbl 1396.91036
Kaminka, Gal A. (ed.) et al., ECAI 2016. 22nd European conference on artificial intelligence, The Hague, Netherlands, August 29 – September 2, 2016. Proceedings. Including proceedings of the accompanied conference on prestigious applications of intelligent systems (PAIS 2016). In 2 volumes. Amsterdam: IOS Press (ISBN 978-1-61499-671-2/pbk; 978-1-61499-672-9/ebook). Frontiers in Artificial Intelligence and Applications 285, 533-541 (2016).
Summary: In multiagent systems the capability of learning is important for an agent to behave appropriately in face of unknown opponents and a dynamic environment. From the system designer’s perspective, it is desirable if the agents can learn to coordinate towards socially optimal outcomes, while also avoiding being exploited by selfish opponents. To this end, we propose a novel gradient ascent based algorithm (SA-IGA) which augments the basic gradient-ascent algorithm by incorporating social awareness into the policy update process. We theoretically analyze the learning dynamics of SA-IGA using dynamical system theory, and SA-IGA is shown to have linear dynamics for a wide range of games including symmetric games. The learning dynamics of two representative games (the prisoner’s dilemma game and coordination game) are analyzed in detail. Based on the idea of SA-IGA, we further propose a practical multiagent learning algorithm, called SA-PGA, based on the Q-learning update rule. Simulation results show that an SA-PGA agent can achieve higher social welfare than previous social-optimality oriented conditional joint action learner (CJAL) and also is robust against individually rational opponents by reaching Nash equilibrium solutions.
For the entire collection see [Zbl 1352.68013].
91A26 Rationality and learning in game theory
91A05 2-person games
91A20 Multistage and repeated games
91-04 Software, source code, etc. for problems pertaining to game theory, economics, and finance
Full Text: DOI