FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs

by   Alekh Agarwal, et al.

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.


page 1

page 2

page 3

page 4


Representation Learning for Online and Offline RL in Low-rank MDPs

This work studies the question of Representation Learning in RL: how can...

Model-free Representation Learning and Exploration in Low-rank MDPs

The low rank MDP has emerged as an important model for studying represen...

On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL

We study reward-free reinforcement learning (RL) under general non-linea...

Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning

Value-function (VF) approximation is a central problem in Reinforcement ...

Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning

In view of its power in extracting feature representation, contrastive s...

A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning

Representation learning lies at the heart of the empirical success of de...

Making Linear MDPs Practical via Contrastive Representation Learning

It is common to address the curse of dimensionality in Markov decision p...