Search Results for author:
Found 7 papers, 0 papers with code
Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
Algorithms based on regret matching, specifically regret matching$^+$ (RM$^+$), and its variants are the most popular approaches for solving large-scale two-player zero-sum games in practice.
On the convex formulations of robust Markov decision processes
Our work opens a new research direction for RMDPs and can serve as a first step toward obtaining a tractable convex formulation of RMDPs.
The Best Decisions Are Not the Best Advice: Making Adherence-Aware Recommendations
Many high-stake decisions follow an expert-in-loop structure in that a human operator receives recommendations from an algorithm but is the ultimate decision maker.
Solving optimization problems with Blackwell approachability
We introduce the Conic Blackwell Algorithm$^+$ (CBA$^+$) regret minimizer, a new parameter- and scale-free regret minimizer for general convex sets.
Interpretable Machine Learning for Resource Allocation with Application to Ventilator Triage
We propose a novel data-driven model to compute interpretable triage guidelines based on policies for Markov Decision Process that can be represented as simple sequences of decision trees ("tree policies").
Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving
We develop new parameter-free and scale-free algorithms for solving convex-concave saddle-point problems.
Scalable First-Order Methods for Robust MDPs
Our framework is also the first one to solve robust MDPs with $s$-rectangular KL uncertainty sets.
