Socially-Aware Multiagent Learning: Towards Socially Optimal Outcomes

نویسندگان

  • Xiaohong Li
  • Chengwei Zhang
  • Jianye Hao
  • Karl Tuyls
  • Siqi Chen
  • Zhiyong Feng
چکیده

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.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

SA-IGA: A Multiagent Reinforcement Learning Method Towards Socially Optimal Outcomes

In multiagent environments, the capability of learning is important for an agent to behave appropriately in face of unknown opponents and 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 bas...

متن کامل

Towards Socially Aware Mobile Phones

Mobile phones currently represent the most pervasive technology for enabling social networking. They collect a wide range of socially meaningful data, such as address book contacts, pictures, call logs and exchanged messages. This data, however, is highly underutilized as it is managed by separate applications which are typically unaware of the user’s social setting. This “unawareness” makes th...

متن کامل

Socially-Aware Informal Learning Support: Potentials and Challenges of the Social Dimension

With increasingly conceiving learning as a social activity, technological support must become more aware of the social context of the individual in order to be able to provide adequate support. But many issues related to making systems socially aware are subject to ongoing research, e.g., the description and mining social relationships, and especially privacy preservation. This paper wants to g...

متن کامل

Towards the Development of a Socially-Informed, Process-Oriented Model of Research in Metadiscourse

Since the early development of interest in the interpersonal dimensions of academic communication in the 1980s, the analytic potentials of the concept of metadiscourse have motivated a large number of investigations. Although these analytic potentials have facilitated the study of diverse academic genres, there has always been a risk of detachment of textual analyses form the contextual origins...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2016