FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
NIPS 2020, 2020.
We provide several structural results for low rank MDPs, relating it to other models studied in prior work on representation learning for Reinforcement Learning
In order to deal with the curse of dimensionality in reinforcement learning (RL), it is common practice to make parametric assumptions where values or policies are functions of some low dimensional feature space. This work focuses on the representation learning question: how can we learn such features? Under the assumption that the unde...More
PPT (Upload PPT)