Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning
Adaptive Multi-Reward Projection is proposed, a lightweight online method that reallocates aggregation weights using three signals, relative shortfall, reward volatility, and recent progress, increasing pressure on lagging, unstable, or stagnant dimensions while relieving saturated ones.
Yu Yuan, Yao Fan, Lili Zhao et al.
· 2 citations