Communicating via Markov Decision Processes

TL;DR

This paper introduces MEME, a novel approach for communication via Markov decision processes that balances information transfer and cost, demonstrating strong empirical performance in complex, noisy environments.

Contribution

It presents MEME, a theoretically grounded algorithm based on maximum entropy reinforcement learning and minimum entropy coupling, applicable to practical large-scale MCGs.

Findings

MEME outperforms strong baselines on small MCGs.

MEME achieves lossless communication of images in complex environments.

MEME performs well even with actuator noise.

Abstract

We consider the problem of communicating exogenous information by means of Markov decision process trajectories. This setting, which we call a Markov coding game (MCG), generalizes both source coding and a large class of referential games. MCGs also isolate a problem that is important in decentralized control settings in which cheap-talk is not available -- namely, they require balancing communication with the associated cost of communicating. We contribute a theoretically grounded approach to MCGs based on maximum entropy reinforcement learning and minimum entropy coupling that we call MEME. Due to recent breakthroughs in approximation algorithms for minimum entropy coupling, MEME is not merely a theoretical algorithm, but can be applied to practical settings. Empirically, we show both that MEME is able to outperform a strong baseline on small MCGs and that MEME is able to achieve strong performance on extremely large MCGs. To the latter point, we demonstrate that MEME is able to losslessly communicate binary images via trajectories of Cartpole and Pong, while simultaneously achieving the maximal or near maximal expected returns, and that it is even capable of performing well in the presence of actuator noise.