78 citations · 333 across the 57 of their papers we have counts for
12 papers · 1 filter
Global Convergence of Policy Gradient for Sequential Zero-Sum Linear Quadratic Dynamic Games
Jingjing Bu, Lillian J. Ratliff, Mehran Mesbahi
We propose projection-free sequential algorithms for linear-quadratic dynamics games. These policy gradient based algorithms are akin to Stackelberg leadership model and can be ext…
Sensitivity Analysis for Markov Decision Process Congestion Games
Sarah H. Q. Li, Daniel Calderone, Lillian Ratliff +1
We consider a non-atomic congestion game where each decision maker performs selfish optimization over states of a common MDP. The decision makers optimize for their own expected co…
Adaptive Constraint Satisfaction for Markov Decision Process Congestion Games: Application to Transportation Networks
Sarah H. Q. Li, Yue Yu, Nicolas Miguel +3
Under the Markov decision process (MDP) congestion game framework, we study the problem of enforcing population distribution constraints on a population of players with stochastic…
Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games
Eric Mazumdar, Lillian J. Ratliff, Michael I. Jordan +1
We show by counterexample that policy-gradient algorithms have no guarantees of even local convergence to Nash equilibria in continuous action and state space multi-agent settings.…
Sequential Experimental Design for Transductive Linear Bandits
Tanner Fiez, Lalit Jain, Kevin Jamieson +1
In this paper we introduce the transductive linear bandit problem: given a set of measurement vectors , a set of items $\mathcal{Z}\subset \mathbb{…
Convergence of Learning Dynamics in Stackelberg Games
Tanner Fiez, Benjamin Chasnov, Lillian J. Ratliff
This paper investigates the convergence of learning dynamics in Stackelberg games. In the class of games we consider, there is a hierarchical game being played between a leader and…