Problem
Research questions and friction points this paper is trying to address.
multi-objective RL
non-linear utility
timescale
successor features
It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning
🤖 AI Summary
论文指出当前多目标强化学习方法无法处理不同时间尺度上的非线性效用问题，并通过实例说明该问题的重要性。
📝 Abstract
Time is of the essence when dealing with multiple reward signals and non-linear utility. In this paper we argue that the current main approaches in multi-objectiveRL (SER and ESR), and successor features, are insufficient. While each approach deals with non-linear effects on user utility on different timescales, none of them take into account that different effects happening on different timescales can happen within the same decision problem. We motivate that this can indeed be the case by an example, both intuitively and numerically, leading to a new perspective, and a significant and non-trivial gap in the literature.
Innovation
Methods, ideas, or system contributions that make the work stand out.
non-linear utility
multi-objective reinforcement learning
successor features
timescales
🔎 Similar Papers
