EvoRS: On-Policy Self-Evolution of Reward Systems for Open-Ended Reinforcement Learning
EvoRS is introduced, a self-evolving RL framework that evolves the reward system from on-policy experience, representing it as an executable Reward-DAG, and is updated from on-policy rollouts and reward traces to maintain train-time reliability.
Wei-Yuan Li, Ai-Li Chen, Xin-Tao Wang et al.
· 1 citation