Skip to yearly menu bar Skip to main content


Poster Fri, Dec 11, 2026 • 9:00 PM – 11:00 PM AEDT Paris Poster Hall #P137

Safe Offline Reinforcement Learning using Behavior Regularisation and Latent Feasibility-Guidance

Mahesh Keswani ⋅ Parth Bhardwaj ⋅ Ankur Kumar ⋅ Raunak Pushpak Bhattacharyya

Abstract

Log in and register to view live content