Bora Yongacoglu
YOU?
Author Swipe
View article: Paths to Equilibrium in Games
Paths to Equilibrium in Games Open
In multi-agent reinforcement learning (MARL) and game theory, agents repeatedly interact and revise their strategies as new data arrives, producing a sequence of strategy profiles. This paper studies sequences of strategies satisfying a pa…
View article: Generalizing Better Response Paths and Weakly Acyclic Games
Generalizing Better Response Paths and Weakly Acyclic Games Open
Weakly acyclic games generalize potential games and are fundamental to the study of game theoretic control. In this paper, we present a generalization of weakly acyclic games, and we observe its importance in multi-agent learning when agen…
View article: Satisficing Paths and Independent Multiagent Reinforcement Learning in Stochastic Games
Satisficing Paths and Independent Multiagent Reinforcement Learning in Stochastic Games Open
In multiagent reinforcement learning, independent learners are those that do not observe the actions of other agents in the system. Due to the decentralization of information, it is challenging to design independent learners that drive pla…
View article: Unsynchronized Decentralized Q-Learning: Two Timescale Analysis By Persistence
Unsynchronized Decentralized Q-Learning: Two Timescale Analysis By Persistence Open
Non-stationarity is a fundamental challenge in multi-agent reinforcement learning (MARL), where agents update their behaviour as they learn. Many theoretical advances in MARL avoid the challenge of non-stationarity by coordinating the poli…
View article: Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games
Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games Open
Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL). Recent advances in MARL have focused primarily on games with finitely many states. In this work, we study multi-agent learning in stochastic g…
View article: Mean-Field Games With Finitely Many Players: Independent Learning and Subjectivity
Mean-Field Games With Finitely Many Players: Independent Learning and Subjectivity Open
Independent learners are agents that employ single-agent algorithms in multi-agent systems, intentionally ignoring the effect of other strategic agents. This paper studies mean-field games from a decentralized learning perspective, with tw…
View article: Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games With Local Control and Global State Information
Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games With Local Control and Global State Information Open
Stochastic dynamic teams and games are rich models for decentralized systems and challenging testing grounds for multi-agent learning. Previous work that guaranteed team optimality assumed stateless dynamics, or an explicit coordination me…
View article: An Independent Learning Algorithm for a Class of Symmetric Stochastic Games
An Independent Learning Algorithm for a Class of Symmetric Stochastic Games Open
In multi-agent reinforcement learning, independent learners are those that do not access the action selections of other learning agents in the system. This paper investigates the feasibility of using independent learners to find approximat…
View article: Satisficing Paths and Independent Multi-Agent Reinforcement Learning in Stochastic Games
Satisficing Paths and Independent Multi-Agent Reinforcement Learning in Stochastic Games Open
In multi-agent reinforcement learning (MARL), independent learners are those that do not observe the actions of other agents in the system. Due to the decentralization of information, it is challenging to design independent learners that d…
View article: Reinforcement Learning for Decentralized Stochastic Control and Coordination Games
Reinforcement Learning for Decentralized Stochastic Control and Coordination Games Open