Anas Barakat

[Submitted on 3 Oct 2024 ( v1 ), last revised 17 Feb 2026 (this version, v4)] Title:Policy Gradients for Cumulative Prospect Theory in Reinforcement Learning View a PDF of the paper titled Policy Gradients for Cumulative Prospect Theory in Reinforcement Learning, by Olivier Lepel and 1 other authors View PDF HTML (experimental) Abstract:We derive a policy gradient theorem for Cumulative Prospect Theory (CPT) objectives in finite-horizon Reinforcement Learning (RL), generalizing the standard...

[Submitted on 8 Sep 2023 ( v1 ), last revised 29 Oct 2023 (this version, v2)] Title:Learning in Zero-Sum Linear Quadratic Games with Last-Iterate Convergence Download a PDF of the paper titled Learning in Zero-Sum Linear Quadratic Games with Last-Iterate Convergence, by Jiduan Wu and Anas Barakat and Ilyas Fatkhullin and Niao He Download PDF Abstract:Zero-sum Linear Quadratic (LQ) games are fundamental in optimal control and can be used (i)~as a dynamic game formulation for risk-sensitive or...