Reinforcement Learning from Human Feedback (RLHF) has emerged as a critical approach for aligning large language models with human preferences, witnessing rapid algorithmic evolution through methods such as Proximal Policy Optimization (PPO), Direct Preference Optimization (DPO), REINFORCE Leave One-Out (RLOO), ReMax, and Group Relative Policy Optimization (GRPO). We present REINFORCE++, an enhanced variant of the classical REINFORCE algorithm that incorporates key optimization techniques from PPO while eliminating the need for a critic network. REINFORCE++ achieves three primary objectives: (1) simplicity (2) enhanced training stability, and (3) reduced computational overhead. Through extensive empirical evaluation, we demonstrate that REINFORCE++ exhibits superior stability compared to GRPO and achieves greater computational efficiency than PPO while maintaining comparable performance. The implementation is available at \url{https://github.com/OpenRLHF/OpenRLHF}.
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Reinforcement Learning from Human Feedback (RLHF) has emerged as a critical approach for aligning large language models with human preferences, witnessing rapid algorithmic evolution through methods such as Proximal Policy Optimization (PPO), Direct Preference Optimization (DPO),
- Year
- 2025
- Venue
- arXiv 2025
- Authors
- 1
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2501.03262ARXIV-DEFAULT
- TL;DR
- Semantic Scholar