Author name: Shashank Sharma, Janina Hoffmann, Vinay Namboodiri

MRS: Multi-Resolution Skills for HRL Agents

Shashank Sharma, Janina Hoffmann, Vinay Namboodiri / April 22, 2026

arXiv:2505.21410v2 Announce Type: replace-cross
Abstract: Hierarchical reinforcement learning (HRL) decomposes the policy into a manager and a worker, enabling long-horizon planning but introducing a performance gap on tasks requiring agility. We iden…

cs.AI

OLLM: Options-based Large Language Models

Shashank Sharma, Janina Hoffmann, Vinay Namboodiri / April 22, 2026

arXiv:2604.19087v1 Announce Type: new
Abstract: We introduce Options LLM (OLLM), a simple, general method that replaces the single next-token prediction of standard LLMs with a \textit{set of learned options} for the next token, indexed by a discrete …