CORTEXA
← Browse

Ahad Jawaid

1 paper indexed

arxivcs.LG2026-07-23

Offline RL with Hierarchical Action Chunking

Ahad Jawaid

Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets. However, scaling these methods to long-horizon tasks remains a challenge due to the curse of horizon, where value estimation errors can compound throu…

View free PDFSource page