Faster, More Efficient RLHF through Off-Policy Asynchronous Learning

To achieve state-of-the-art chatbots, large language models are finetuned with reinforcement learning (RL), frequently to optimize human feedback (RLHF). This process is computationally expensive and can take weeks. Offline approaches, like DPO, learn on a static dataset and are efficient but not performant. The dominant paradigm, online and on-policy---synchronously generating from the model, labelling with a reward model, and learning on feedback from the model's own outputs---is performant but not efficient. Following prior work in the generall deep RL setting, we propose separating the actor and learner in RLHF. This enables the asynchronously generation of new samples while learning on prior samples, thus leading to overall faster training and better scaling. But this requires a novel regime for RLHF, online but off-policy: learning on samples from a previous version of our model. We ask a fundamental question: how much off-policyness can we tolerate for asynchronous training to speed up learning but maintain performance? We find that a contrastive loss, Online DPO, is most robust to off-policy data and that robustness increases with the scale of the policy model. We show even further compute optimizations but demonstrate that they come at a performance cost, giving rise to a trade-off. Finally, we verify our design choices by training LLaMA 3.1 8B with RLHF as a helpful chatbot in half the time of a synchronous run while matching final performance.