ICLR2025

Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research

Michal Bortkiewicz, Wladyslaw Palucki, Vivek Myers, Tadeusz Dziarmaga, Tomasz Arczewski, Lukasz Kucinski, Benjamin Eysenbach

Abstract

We invite you to collaborate on number of exciting challenges: • Integration of discrete environments and new arm manipulation tasks. • Inverse RL and preference learning pipelines based on JaxGCRL. • Autonomous goal sampling and exploration strategies. Research conducted so far with the help of JaxGCRL: