Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation (opens in new tab)  📈Search Quality  Content type: Academic

Reinforcement learning (RL) presents a promising avenue for enhancing generative recommendation beyond supervised imitation, leveraging reward signals to guide policy improvement. However, its efficacy is critically contingent on the trustworthiness of the reward model for the samples it evaluates. In practice, production rankers, the widely adopted reward models, are trained on exposure-biased logs, leading to sample-dependent inaccuracies th...