FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
This addresses the curse of dimensionality in RL for researchers and practitioners by generalizing prior formulations for representation learning.
The paper tackles the problem of representation learning in reinforcement learning under low rank transition models, showing that it relates to a non-linear matrix decomposition problem and developing the FLAMBE algorithm for provably efficient RL.
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 underlying (unknown) dynamics correspond to a low rank transition matrix, we show how the representation learning question is related to a particular non-linear matrix decomposition problem. Structurally, we make precise connections between these low rank MDPs and latent variable models, showing how they significantly generalize prior formulations for representation learning in RL. Algorithmically, we develop FLAMBE, which engages in exploration and representation learning for provably efficient RL in low rank transition models.