Twice regularized MDPs and the equivalence between robustness and regularization

by   Esther Derman, et al.

Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robust MDPs with uncertain reward. We thus establish that policy iteration on reward-robust MDPs can have the same time complexity as on regularized MDPs. We further extend this relationship to MDPs with uncertain transitions: this leads to a regularization term with an additional dependence on the value function. We finally generalize regularized MDPs to twice regularized MDPs (R^2 MDPs), i.e., MDPs with both value and policy regularization. The corresponding Bellman operators enable developing policy iteration schemes with convergence and robustness guarantees. It also reduces planning and learning in robust MDPs to regularized MDPs.



There are no comments yet.


page 1

page 2

page 3

page 4


Partial Policy Iteration for L1-Robust Markov Decision Processes

Robust Markov decision processes (MDPs) allow to compute reliable soluti...

Distributional Robustness and Regularization in Reinforcement Learning

Distributionally Robust Optimization (DRO) has enabled to prove the equi...

Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability

In the Bayesian reinforcement learning (RL) setting, a prior distributio...

Optimistic Policy Iteration for MDPs with Acyclic Transient State Structure

We consider Markov Decision Processes (MDPs) in which every stationary p...

Scaling Up Robust MDPs by Reinforcement Learning

We consider large-scale Markov decision processes (MDPs) with parameter ...

Bounding Fixed Points of Set-Based Bellman Operator and Nash Equilibria of Stochastic Games

Motivated by uncertain parameters encountered in Markov decision process...

Scalable First-Order Methods for Robust MDPs

Markov Decision Processes (MDP) are a widely used model for dynamic deci...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.