Non-maximizing policies that fulfill multi-criterion aspirations in expectation

Abstract

In dynamic programming and reinforcement learning, the policy for the sequential decision making of an agent in a stochastic environment is usually determined by expressing the goal as a scalar reward function and seeking a policy that maximizes the expected total reward. However, many goals that humans care about naturally concern multiple aspects of the world, and it may not be obvious how to condense those into a single reward function. Furthermore, maximization suffers from specification gaming, where the obtained policy achieves a high expected total reward in an unintended way, often taking extreme or nonsensical actions. Here we consider finite acyclic Markov Decision Processes with multiple distinct evaluation metrics, which do not necessarily represent quantities that the user wants to be maximized. We assume the task of the agent is to ensure that the vector of expected totals of the evaluation metrics falls into some given convex set, called the aspiration set. Our algorithm guarantees that this task is fulfilled by using simplices to approximate feasibility sets and propagate aspirations forward while ensuring they remain feasible. It has complexity linear in the number of possible state-action-successor triples and polynomial in the number of evaluation metrics. Moreover, the explicitly non-maximizing nature of the chosen policy and goals yields additional degrees of freedom, which can be used to apply heuristic safety criteria to the choice of actions. We discuss several such safety criteria that aim to steer the agent towards more conservative behavior.