Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty

10/10/2020
by   Reazul Hasan Russel, et al.
0

In this paper, we focus on the problem of robustifying reinforcement learning (RL) algorithms with respect to model uncertainties. Indeed, in the framework of model-based RL, we propose to merge the theory of constrained Markov decision process (CMDP), with the theory of robust Markov decision process (RMDP), leading to a formulation of robust constrained-MDPs (RCMDP). This formulation, simple in essence, allows us to design RL algorithms that are robust in performance, and provides constraint satisfaction guarantees, with respect to uncertainties in the system's states transition probabilities. The need for RCMPDs is important for real-life applications of RL. For instance, such formulation can play an important role for policy transfer from simulation to real world (Sim2Real) in safety critical applications, which would benefit from performance and safety guarantees which are robust w.r.t model uncertainty. We first propose the general problem formulation under the concept of RCMDP, and then propose a Lagrangian formulation of the optimal problem, leading to a robust-constrained policy gradient RL algorithm. We finally validate this concept on the inventory management problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/05/2021

Lyapunov Robust Constrained-MDPs: Soft-Constrained Robustly Stable Policy Optimization under Model Uncertainty

Safety and robustness are two desired properties for any reinforcement l...
research
08/01/2020

Learning with Safety Constraints: Sample Complexity of Reinforcement Learning for Constrained MDPs

Many physical systems have underlying safety considerations that require...
research
08/22/2023

Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes

The robust constrained Markov decision process (RCMDP) is a recent task-...
research
11/10/2022

Safety-Constrained Policy Transfer with Successor Features

In this work, we focus on the problem of safe policy transfer in reinfor...
research
02/02/2023

Average-Constrained Policy Optimization

Reinforcement Learning (RL) with constraints is becoming an increasingly...
research
01/24/2022

Constrained Policy Optimization via Bayesian World Models

Improving sample-efficiency and safety are crucial challenges when deplo...
research
07/15/2023

Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation

Robustness has been extensively studied in reinforcement learning (RL) t...

Please sign up or login with your details

Forgot password? Click here to reset