PAC Bounds for Imitation and Model-based Batch Learning of Contextual Markov Decision Processes
Nair, Yash, Doshi-Velez, Finale
We consider the problem of batch multi-task reinforcement learning with observed context descriptors, motivated by its application to personalized medical treatment. In particular, we study two general classes of learning algorithms: direct policy learning (DPL), an imitation-learning based approach which learns from expert trajectories, and model-based learning. First, we derive sample complexity bounds for DPL, and then show that model-based learning from expert actions can, even with a finite model class, be impossible. After relaxing the conditions under which the model-based approach is expected to learn by allowing for greater coverage of state-action space, we provide sample complexity bounds for model-based learning with finite model classes, showing that there exist model classes with sample complexity exponential in their statistical complexity. We then derive a sample complexity upper bound for model-based learning based on a measure of concentration of the data distribution. Our results give formal justification for imitation learning over model-based learning in this setting.
Jul-17-2020
- Country:
- North America > United States
- Massachusetts > Middlesex County > Cambridge (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America > United States
- Genre:
- Instructional Material > Course Syllabus & Notes (0.86)
- Research Report (0.84)
- Industry:
- Health & Medicine > Therapeutic Area > Immunology (0.46)