Alex DeWeese

According to our database, Alex DeWeese authored at least 4 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with <i>k</i>-step Policy Gradients.

Alex DeWeese, Guannan Qu

CoRR, May, 2026

2025

Thinking Beyond Visibility: A Near-Optimal Policy Framework for Locally Interdependent Multi-Agent MDPs.

Alex DeWeese, Guannan Qu

CoRR, June, 2025

2024

Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies.

Alex DeWeese, Guannan Qu

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2021

BEAR: Sketching BFGS Algorithm for Ultra-High Dimensional Feature Selection in Sublinear Memory.

Amirali Aghazadeh, Vipul Gupta, Alex DeWeese, Onur Ozan Koyluoglu, Kannan Ramchandran

Proceedings of the Mathematical and Scientific Machine Learning, 2021