Composable modular reinforcement learning

Abstract

Modular reinforcement learning (MRL) decomposes a monolithic multiple-goal problem into modules that solve a portion of the original problem. The modules' action preferences are arbitrated to determine the action taken by the agent. Truly modular reinforcement learning would support not only decomposition into modules, but composability of separately written modules in new modular reinforcement learning agents. However, the performance of MRL agents that arbitrate module preferences using additive reward schemes degrades when the modules have incomparable reward scales. This performance degradation means that separately written modules cannot be composed in new modular reinforcement learning agents as-is - they may need to be modified to align their reward scales. We solve this problem with a Q-learning-based command arbitration algorithm and demonstrate that it does not exhibit the same performance degradation as existing approaches to MRL, thereby supporting composability.