On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks
This work highlights fundamental limitations in standard RL reward formulations, potentially affecting researchers and practitioners designing reward systems for complex tasks.
The paper investigates the expressivity of scalar, Markovian reward functions in reinforcement learning, finding that they cannot represent most instances of multi-objective, risk-sensitive, and modal tasks, with derived necessary and sufficient conditions for each class.
In this paper, we study the expressivity of scalar, Markovian reward functions in Reinforcement Learning (RL), and identify several limitations to what they can express. Specifically, we look at three classes of RL tasks; multi-objective RL, risk-sensitive RL, and modal RL. For each class, we derive necessary and sufficient conditions that describe when a problem in this class can be expressed using a scalar, Markovian reward. Moreover, we find that scalar, Markovian rewards are unable to express most of the instances in each of these three classes. We thereby contribute to a more complete understanding of what standard reward functions can and cannot express. In addition to this, we also call attention to modal problems as a new class of problems, since they have so far not been given any systematic treatment in the RL literature. We also briefly outline some approaches for solving some of the problems we discuss, by means of bespoke RL algorithms.