Tal Fiskus

MS student, Bar-Ilan University

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound

#315 · Tal Fiskus, Uri Shaham

This paper presents SUFT, a causal upper-bound loss optimization strategy for DRL designed to enhance sample efficiency and reduce computational demands.