logo
today local_bar
compute scaling

1 paper across 1 session

Poster Session 2

1 paper
Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
#305 · Michal Nauman, Marek Cygan, Carmelo Sferrazza, Aviral Kumar, Pieter Abbeel

We find that online multi-task RL with high-capacity value models leads to SOTA sample efficiency and performance