Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem
F Kalogiannis, J Yan, I Panageas - arXiv preprint arXiv:2410.05673, 2024 - arxiv.org
We study the problem of learning a Nash equilibrium (NE) in Markov games which is a
cornerstone in multi-agent reinforcement learning (MARL). In particular, we focus on infinite …
cornerstone in multi-agent reinforcement learning (MARL). In particular, we focus on infinite …
Convex Markov Games: A Framework for Creativity, Imitation, Fairness, and Safety in Multiagent Learning
Behavioral diversity, expert imitation, fairness, safety goals and others give rise to
preferences in sequential decision making domains that do not decompose additively …
preferences in sequential decision making domains that do not decompose additively …
Solving hidden monotone variational inequalities with surrogate losses
Deep learning has proven to be effective in a wide variety of loss minimization problems.
However, many applications of interest, like minimizing projected Bellman error and min …
However, many applications of interest, like minimizing projected Bellman error and min …
Efficient Algorithms for a Class of Stochastic Hidden Convex Optimization and Its Applications in Network Revenue Management
We study a class of stochastic nonconvex optimization in the form of min x∈ XF (x)≔ E ξ [f (ϕ
(x, ξ))], that is, F is a composition of a convex function f and a random function ϕ. Leveraging …
(x, ξ))], that is, F is a composition of a convex function f and a random function ϕ. Leveraging …
Statistical Inference in Latent Convex Objectives with Stream Data
R Chauhan, EV Vlatakis-Gkaragkounis… - OPT 2024: Optimization … - openreview.net
Stochastic gradient methods are increasingly employed in statistical inference tasks, such as
parameter and interval estimation. Yet, much of the current theoretical framework mainly …
parameter and interval estimation. Yet, much of the current theoretical framework mainly …