WARP: On the Benefits of Weight Averaged Rewarded Policies
WARP: On the Benefits of Weight Averaged Rewarded Policies
Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) by encouraging their generations to have high rewards, using a reward model trained on human preferences. To prevent the forgetting of pre-trained knowledge, RLHF usually incorporates a KL regularization; this forces the policy to remain close to its supervised …