Timezone: »

 
Poster
Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
Shengpu Tang · Maggie Makar · Michael Sjoding · Finale Doshi-Velez · Jenna Wiens

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #307
in Poster Session 3 »

Many reinforcement learning (RL) applications have combinatorial action spaces, where each action is a composition of sub-actions. A standard RL approach ignores this inherent factorization structure, resulting in a potential failure to make meaningful inferences about rarely observed sub-action combinations; this is particularly problematic for offline settings, where data may be limited. In this work, we propose a form of linear Q-function decomposition induced by factored action spaces. We study the theoretical properties of our approach, identifying scenarios where it is guaranteed to lead to zero bias when used to approximate the Q-function. Outside the regimes with theoretical guarantees, we show that our approach can still be useful because it leads to better sample efficiency without necessarily sacrificing policy optimality, allowing us to achieve a better bias-variance trade-off. Across several offline RL problems using simulators and real-world datasets motivated by healthcare, we demonstrate that incorporating factored action spaces into value-based RL can result in better-performing policies. Our approach can help an agent make more accurate inferences within underexplored regions of the state-action space when applying RL to observational datasets.

Keywords: Reinforcement Learning · healthcare · offline RL · Domain Knowledge · bias-variance trade-off · action space factorization · sepsis
[ Paper]  [ Slides]  [ Poster]  [ OpenReview] 

Author Information

Shengpu Tang (University of Michigan)
Maggie Makar (University of Michigan)
Michael Sjoding (University of Michigan - Ann Arbor)
Finale Doshi-Velez (Harvard)
Jenna Wiens (University of Michigan)

More from the Same Authors