Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
This work addresses data efficiency in RL for continuous domains, offering incremental theoretical insights into stability and convergence.
The paper tackles the challenge of data-hungry reinforcement learning in continuous spaces by introducing a framework that proves fast convergence rates in offline and online settings, demonstrating stability properties in many continuous Markov decision processes.
We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights two key stability properties, relating to how changes in value functions and/or policies affect the Bellman operator and occupation measures. We argue that these properties are satisfied in many continuous state-action Markov decision processes, and demonstrate how they arise naturally when using linear function approximation methods. Our analysis offers fresh perspectives on the roles of pessimism and optimism in off-line and on-line RL, and highlights the connection between off-line RL and transfer learning.