Publications

Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training
Anas Barakat, Souradip Chakraborty, Khushbu Pahwa, Amrit Singh Bedi
Arxiv
Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria
Anas Barakat, Ioannis Panageas, Antonios Varvitsiotis
Arxiv
Policy Gradients for Cumulative Prospect Theory in Reinforcement Learning
Olivier Lepel, Anas Barakat
Slides Arxiv
On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
Anas Barakat, Souradip Chakraborty, Peihong Yu, Pratap Tokekar, Amrit Singh Bedi
Poster Proceedings Arxiv
Online Multi-Agent Control with Adversarial Disturbances
Anas Barakat, John Lazarsfeld, Georgios Piliouras, Antonios Varvitsiotis
Slides Arxiv
Optimistic Online Learning in Symmetric Cone Games
Anas Barakat, Wayne Lin, John Lazarsfeld, Antonios Varvitsiotis
Slides Journal Arxiv
Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last Iterate Convergence
Jiduan Wu, Anas Barakat, Ilyas Fatkhullin, Niao He
Journal Arxiv
Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players
Pragnya Alatur, Anas Barakat*, Niao He
Slides Proceedings Arxiv
Policy Mirror Descent with Lookahead
Kimon Protopapas, Anas Barakat
Poster Proceedings Arxiv
Independent Learning in Constrained Markov Potential Games
Philip Jordan, Anas Barakat, Niao He
Poster Slides Proceedings Arxiv
Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity
Jiduan Wu, Anas Barakat, Ilyas Fatkhullin, Niao He
Proceedings Arxiv
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
Anas Barakat, Ilyas Fatkhullin, Niao He
Poster Slides Proceedings Arxiv
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
Ilyas Fatkhullin, Anas Barakat, Anastasia Kireeva, Niao He
Poster Proceedings Arxiv
Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation
Anas Barakat, Pascal Bianchi, Julien Lehmann
Poster Proceedings Arxiv
Contributions to non-convex stochastic optimization and reinforcement learning
Anas Barakat
Slides Thesis
Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance
Anas Barakat, Pascal Bianchi, Walid Hachem, Sholom Schechtman
DOI Arxiv Journal
Convergence and Dynamical Behavior of the ADAM Algorithm for Non-Convex Stochastic Optimization
Anas Barakat, Pascal Bianchi
Poster Slides Video DOI Arxiv Journal
Convergence Rates of a Momentum Algorithm with Bounded Adaptive Step Size for Non-Convex Optimization
Anas Barakat, Pascal Bianchi
Poster Slides Proceedings Arxiv