Compartmental observability approach for the optimal transparency problem in multi-agent systems

Arefizadeh, Sadegh; Ozgoli, Sadjaad; Bolouki, Sadegh; Başar, Tamer

doi:10.1016/j.automatica.2022.110398

Cited by 4 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We look at transparency as information availability to agents in a dynamic MAS that can be used to improve their objectives. There is work on studying the impact of information in networks of interacting agents in the game theory literature that involves classifying information in games into two types (Arefizadeh et al 2022). The first type looks at the availability of the rules of the game to players in it, resulting in games with complete or incomplete information (Harsanyi 1967).…”

Section: Transparencymentioning

confidence: 99%

Profit equitably

Dwarakanath

Vyetrenko

Balch

2021

Proceedings of the Second ACM International Conference on AI in Finance

View full text Add to dashboard Cite

Is transparency always beneficial in complex systems such as traffic networks and stock markets? How is transparency defined in multi-agent systems, and what is its optimal degree at which social welfare is highest? We take an agent-based view to define transparency (or its lacking) as delay in agent observability of environment states, and utilize simulations to analyze the impact of delay on social welfare. To model the adaptation of agent strategies with varying delays, we model agents as learners maximizing the same objectives under different delays in a simulated environment. Focusing on two agent types -constrained and unconstrained, we use multi-agent reinforcement learning to evaluate the impact of delay on agent outcomes and social welfare. Empirical demonstration of our framework in simulated financial markets shows opposing trends in outcomes of the constrained and unconstrained agents with delay, with an optimal partial transparency regime at which social welfare is maximal.

show abstract

Section: Transparencymentioning

confidence: 99%