← all papers · overview

MA-RLHF: Reinforcement Learning From Human Feedback With Macro Actions

Abstract

Reinforcement learning from human feedback (RLHF) has demonstrated effectiveness in aligning large language models (LLMs) with human preferences. However, token-level RLHF suffers from the credit assignment problem over long sequences, where delayed rewards make it challenging for the model to discern which actions contributed to preferred outcomes. This hinders learning efficiency and slows conve

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).