Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond

TL;DR

This paper analyzes the role of reinforcement learning in large language models, especially RLHF, highlighting its techniques, advantages, challenges, and future directions to improve instruction-following and safety.

Contribution

It clarifies how RLHF relates to traditional RL, explains its effectiveness, and discusses future research avenues in LLM reinforcement learning.

Findings

RLHF is online inverse RL with offline demonstration data.

RLHF outperforms supervised fine-tuning by reducing compounding errors.

The RM step in RLHF can be generalized to other LLM tasks involving expensive feedback.

Abstract

Recent advancements in Large Language Models (LLMs) have garnered wide attention and led to successful products such as ChatGPT and GPT-4. Their proficiency in adhering to instructions and delivering harmless, helpful, and honest (3H) responses can largely be attributed to the technique of Reinforcement Learning from Human Feedback (RLHF). In this paper, we aim to link the research in conventional RL to RL techniques used in LLM research. Demystify this technique by discussing why, when, and how RL excels. Furthermore, we explore potential future avenues that could either benefit from or contribute to RLHF research. Highlighted Takeaways: 1. RLHF is Online Inverse RL with Offline Demonstration Data. 2. RLHF $>$ SFT because Imitation Learning (and Inverse RL) $>$ Behavior Cloning (BC) by alleviating the problem of compounding error. 3. The RM step in RLHF generates a proxy of the expensive human feedback, such an insight can be generalized to other LLM tasks such as prompting evaluation and optimization where feedback is also expensive. 4. The policy learning in RLHF is more challenging than conventional problems studied in IRL due to their high action dimensionality and feedback sparsity. 5. The main superiority of PPO over off-policy value-based methods is its stability gained from (almost) on-policy data and conservative policy updates.