Finite Time Convergence Analysis of Policy Gradient Learning in Stochastic Stackelberg Games

View at publisher Summarise with VIRAT
Authors: Pranoy Das, Muhammad Aneeq uz Zaman, Vijay Gupta
Cited by: 0
References: 32

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Designing and analyzing learning algorithms for general sum stochastic Stackelberg games remains challenging. We propose an inner-outer loop policy gradient-based learning algorithm for this problem and analyze its finite time convergence. Our analysis does not assume a time scale separation between the leader and the follower or a special structure on the game such as being Markov potential or zero-sum.

Fields of Study & Subjects

Game Theory and Applications Adaptive Dynamic Programming Control Reinforcement Learning in Robotics

Publication details

Journal / source
IEEE Transactions on Automatic Control
Volume
71
Issue
9
Pages
6155–6162
Publication date
30 March 2026
Language
EN