78 citations · 205 across the 14 of their papers we have counts for
16 papers
Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation
Jake Gonzales, Max Horwitz, Eric Mazumdar +1
Provably efficient and robust equilibrium computation in general-sum Markov games remains a core challenge in multi-agent reinforcement learning. Nash equilibrium is computationall…
Follower Agnostic Methods for Stackelberg Games
Chinmay Maheshwari, James Cheng, S. Shankar Sasty +2
In this paper, we present an efficient algorithm to solve online Stackelberg games, featuring multiple followers, in a follower-agnostic manner. Unlike previous works, our approach…
Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets
Chinmay Maheshwari, Eric Mazumdar, Shankar Sastry
We study the problem of online learning in competitive settings in the context of two-sided matching markets. In particular, one side of the market, the agents, must learn about th…
Who Leads and Who Follows in Strategic Classification?
Tijana Zrnic, Eric Mazumdar, S. Shankar Sastry +1
As predictive models are deployed into the real world, they must increasingly contend with strategic behavior. A growing body of work on strategic classification treats this proble…
Zeroth-Order Methods for Convex-Concave Minmax Problems: Applications to Decision-Dependent Risk Minimization
Chinmay Maheshwari, Chih-Yuan Chiu, Eric Mazumdar +2
Min-max optimization is emerging as a key framework for analyzing problems of robustness to strategically and adversarially generated data. We propose a random reshuffling-based gr…
Expert Selection in High-Dimensional Markov Decision Processes
Vicenc Rubies-Royo, Eric Mazumdar, Roy Dong +2
In this work we present a multi-armed bandit framework for online expert selection in Markov decision processes and demonstrate its use in high-dimensional settings. Our method tak…
Local Nash Equilibria are Isolated, Strict Local Nash Equilibria in `Almost All' Zero-Sum Continuous Games
Eric Mazumdar, Lillian Ratliff
We prove that differential Nash equilibria are generic amongst local Nash equilibria in continuous zero-sum games. That is, there exists an open-dense subset of zero-sum games for…
Feedback Linearization for Unknown Systems via Reinforcement Learning
Tyler Westenbroek, David Fridovich-Keil, Eric Mazumdar +4
We present a novel approach to control design for nonlinear systems which leverages model-free policy optimization techniques to learn a linearizing controller for a physical plant…
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.…
Convergence Analysis of Gradient-Based Learning with Non-Uniform Learning Rates in Non-Cooperative Multi-Agent Settings
Benjamin Chasnov, Lillian J. Ratliff, Eric Mazumdar +1
Considering a class of gradient-based multi-agent learning algorithms in non-cooperative settings, we provide local convergence guarantees to a neighborhood of a stable local Nash…
On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in Zero-Sum Games
Eric V. Mazumdar, Michael I. Jordan, S. Shankar Sastry
We propose local symplectic surgery, a two-timescale procedure for finding local Nash equilibria in two-player zero-sum games. We first show that previous gradient-based algorithms…
On Gradient-Based Learning in Continuous Games
Eric Mazumdar, Lillian J. Ratliff, S. Shankar Sastry
We formulate a general framework for competitive gradient-based learning that encompasses a wide breadth of multi-agent learning algorithms, and analyze the limiting behavior of co…
A Multi-Armed Bandit Approach for Online Expert Selection in Markov Decision Processes
Eric Mazumdar, Roy Dong, Vicenç Rúbies Royo +2
We formulate a multi-armed bandit (MAB) approach to choosing expert policies online in Markov decision processes (MDPs). Given a set of expert policies trained on a state and actio…
Optimal Causal Imputation for Control
Roy Dong, Eric Mazumdar, S. Shankar Sastry
The widespread applicability of analytics in cyber-physical systems has motivated research into causal inference methods. Predictive estimators are not sufficient when analytics ar…
Inverse Risk-Sensitive Reinforcement Learning
Lillian J. Ratliff, Eric Mazumdar
We address the problem of inverse reinforcement learning in Markov decision processes where the agent is risk-sensitive. In particular, we model risk-sensitivity in a reinforcement…
To Observe or Not to Observe: Queuing Game Framework for Urban Parking
Lillian J. Ratliff, Chase Dowling, Eric Mazumdar +1
We model parking in urban centers as a set of parallel queues and overlay a game theoretic structure that allows us to compare the user-selected (Nash) equilibrium to the socially…