no code implementations • 26 Mar 2024 • Bora Yongacoglu, Gürdal Arslan, Lacra Pavel, Serdar Yüksel
In multi-agent reinforcement learning (MARL), agents repeatedly interact across time and revise their strategies as new data arrives, producing a sequence of strategy profiles.
1 code implementation • 29 Oct 2022 • Zichu Liu, Lacra Pavel
Despite the success of generative adversarial networks (GANs) in generating visually appealing images, they are notoriously challenging to train.
no code implementations • 18 Nov 2021 • Bolin Gao, Lacra Pavel
In this paper, we propose a second-order extension of the continuous-time game-theoretic mirror descent (MD) dynamics, referred to as MD2, which provably converges to mere (but not necessarily strict) variationally stable states (VSS) without using common auxiliary techniques such as time-averaging or discounting.
no code implementations • 23 Apr 2021 • Andrew R. Romano, Lacra Pavel
We show that these dynamics converge to an epsilon-GNE while satisfying the constraints for all time, not only in steady-state.
no code implementations • 7 Dec 2019 • Bolin Gao, Lacra Pavel
In this paper, we consider concave continuous-kernel games characterized by monotonicity properties and propose discounted mirror descent-type dynamics.
no code implementations • 7 Feb 2018 • Mohammadhosein Hasanbeig, Lacra Pavel
The main focus of this paper is on enhancement of two types of game-theoretic learning algorithms: log-linear learning and reinforcement learning.
no code implementations • 3 Apr 2017 • Bolin Gao, Lacra Pavel
In this paper, we utilize results from convex analysis and monotone operator theory to derive additional properties of the softmax function that have not yet been covered in the existing literature.