How to explore to find a robust control policy?

May 10, 2021

This is a post for the work Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning (Curi et al., 2021), jointly with Ilija Bogunovic and Andreas Krause, that will appear in ICML 2021. It is a follow up on Efficient Model-Based reinforcement Learning Through Optimistic Policy Search and Planning (Curi et al., 2020), that appeard in NeuRIPS 2020 (See blog post).