Reinforcement Learning, Bit by Bit
This work addresses data efficiency for reinforcement learning agents transitioning from simulated to real environments, presenting a novel framework with potential broad impact.
The paper tackles the problem of data inefficiency in reinforcement learning for real-world applications by proposing a framework for understanding information acquisition and representation, and demonstrates improved data efficiency with computational results.
Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agents calls for a deeper understanding of information acquisition and representation. We discuss concepts and regret analysis that together offer principled guidance. This line of thinking sheds light on questions of what information to seek, how to seek that information, and what information to retain. To illustrate concepts, we design simple agents that build on them and present computational results that highlight data efficiency.