HOMER Provable Exploration in Reinforcement Learning

Last week at ICML 2020, Mikael Henaff, Akshay Krishnamurthy, John Langford and I had a paper on a new reinforcement learning (RL) algorithm that solves three key problems in RL: (i) global exploration, (ii) decoding latent dynamics, and (iii) optimizing a given reward function. Our ICML poster is here. The paper is a bit mathematically