DeepAI AI Chat
Log In Sign Up

Improving the Robustness of Reinforcement Learning Policies with ℒ_1 Adaptive Control

by   Y. Cheng, et al.
University of Illinois at Urbana-Champaign

A reinforcement learning (RL) control policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. For controlling systems with continuous state and action spaces, we propose an add-on approach to robustifying a pre-trained RLpolicy by augmenting it with an ℒ_1 adaptive controller (ℒ_1AC). Leveraging the capability of an ℒ_1AC for fast estimation and active compensation of dynamic variations, the proposed approach can improve the robustness of an RL policy which is trained either in a simulator or in the real world without consideration of a broad class of dynamic variations. Numerical and real-world experiments empirically demonstrate the efficacy of the proposed approach in robustifying RL policies trained using both model-free and model-based methods. A video for the experiments on a real Pendubot setup is availableat


page 1

page 6

page 7


Robustifying Reinforcement Learning Policies with ℒ_1 Adaptive Control

A reinforcement learning (RL) policy trained in a nominal environment co...

MRAC-RL: A Framework for On-Line Policy Adaptation Under Parametric Model Uncertainty

Reinforcement learning (RL) algorithms have been successfully used to de...

GrowSpace: Learning How to Shape Plants

Plants are dynamic systems that are integral to our existence and surviv...

Learning to Play Soccer by Reinforcement and Applying Sim-to-Real to Compete in the Real World

This work presents an application of Reinforcement Learning (RL) for the...

Deep Inventory Management

We present a Deep Reinforcement Learning approach to solving a periodic ...

RL-Controller: a reinforcement learning framework for active structural control

To maintain structural integrity and functionality during the designed l...

Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning

We investigate policy transfer using image-to-semantics translation to m...