Anas Barakat
Anas Barakat
Home
Research
Talks
Teaching
CV
Contact
Light
Dark
Automatic
Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last Iterate Convergence
Jiduan Wu
,
Anas Barakat
,
Ilyas Fatkhullin
,
Niao He
June 2025
Arxiv
Type
Conference paper
Publication
To appear in SIAM Journal on Control and Optimization
Multi-Agent Learning
Related
Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity
Independent Learning in Constrained Markov Potential Games
Optimistic Online Learning in Symmetric Cone Games
Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
Cite
×