Anas Barakat
Anas Barakat
Home
Research
Talks
Teaching
CV
Contact
Light
Dark
Automatic
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
Ilyas Fatkhullin
,
Anas Barakat
,
Anastasia Kireeva
,
Niao He
February 2023
Poster
Proceedings
Arxiv
Type
Conference paper
Publication
ICML 2023
Related
Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
Independent Learning in Constrained Markov Potential Games
Reinforcement Learning with General Utilities: Scaling to Large State Action Spaces via Occupancy Measure Approximation
Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players
Cite
×