Continual Auxiliary Task Learning
This addresses the challenge of non-stationarity in continual auxiliary task learning for reinforcement learning systems, though it appears incremental as it builds on existing successor features methods.
The paper tackled the problem of adapting behavior policies to gather useful data for off-policy auxiliary task learning in reinforcement learning, resulting in an algorithm based on successor features that improves convergence rates under non-stationary conditions.
Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet there is little work on how to adapt the behavior to gather useful data for those off-policy predictions. In this work, we investigate a reinforcement learning system designed to learn a collection of auxiliary tasks, with a behavior policy learning to take actions to improve those auxiliary predictions. We highlight the inherent non-stationarity in this continual auxiliary task learning problem, for both prediction learners and the behavior learner. We develop an algorithm based on successor features that facilitates tracking under non-stationary rewards, and prove the separation into learning successor features and rewards provides convergence rate improvements. We conduct an in-depth study into the resulting multi-prediction learning system.