Robust Reinforcement Learning

Robust reinforcement learning (RL) focuses on developing RL agents that perform well even when faced with uncertainties in the environment, such as noisy observations, model mismatches, or adversarial attacks. Current research emphasizes techniques like adversarial training, distributionally robust optimization, and the use of pessimistic models to improve robustness, often incorporating actor-critic algorithms, model-based approaches, and Lipschitz-constrained policy networks. This field is crucial for deploying RL agents in real-world settings where perfect knowledge of the environment is unrealistic, impacting areas like robotics, autonomous systems, and finance by enabling safer and more reliable AI.

Papers

June 21, 2022

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Junlin Wu, Yevgeniy Vorobeychik
Adversarial Robustness Adversarial Perturbation Robust Reinforcement Learning Robust Deep Reinforcement Learning Adversarial Curriculum

June 14, 2022

Robust Reinforcement Learning with Distributional Risk-averse formulation
Pierre Clavier, Stéphanie Allassonière, Erwan Le Pennec
Reinforcement Learning Native Robustness Distributional Reinforcement Learning Robust Reinforcement Learning

May 25, 2022

Robust Reinforcement Learning on Graphs for Logistics optimization
Zangir Iklassov, Dmitrii Medvedev
Reinforcement Learning Graph Neural Network Graph Drawing Robust Reinforcement Learning System Optimization

May 15, 2022

Policy Gradient Method For Robust Reinforcement Learning
Yue Wang, Shaofeng Zou
Policy Gradient Robust Policy Robust Reinforcement Learning

April 1, 2022

Hysteresis-Based RL: Robustifying Reinforcement Learning-based Control Policies via Hybrid Control
Jan de Priester, Ricardo G. Sanfelice, Nathan van de Wouw
Reinforcement Learning Proximal Policy Optimization Deep Q Network Robust Reinforcement Learning Hybrid Control Hysteresis Compensation

March 3, 2022

On Practical Reinforcement Learning: Provable Robustness, Scalability, and Statistical Efficiency
Thanh Nguyen-Tang
Reinforcement Learning Optimization Purpose Potential Scalability Distributional Reinforcement Learning Robust Reinforcement Learning Sample Efficiency

February 19, 2022

Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training
Peide Huang, Mengdi Xu, Fei Fang, Ding Zhao
Adversarial Training Robust Reinforcement Learning Stackelberg Game Adversarial Reinforcement Learning

February 17, 2022

Robust Reinforcement Learning via Genetic Curriculum
Yeeho Song, Jeff Schneider
Deep Reinforcement Learning Native Robustness Robust Reinforcement Learning Adversarial Agent Robust Strategy Evolutionary Curriculum

February 15, 2022

User-Oriented Robust Reinforcement Learning
Haoyi You, Beichen Yu, Haiming Jin, Zhaoxing Yang, Jiahui Sun
Reinforcement Learning Robust Reinforcement Learning

February 14, 2022

Robust Policy Learning over Multiple Uncertainty Sets
Annie Xie, Shagun Sodhani, Chelsea Finn, Joelle Pineau, Amy Zhang
Reinforcement Learning Native Robustness Robust Policy Robust Reinforcement Learning Uncertainty Set Robust Controllable Set

February 12, 2022

Robust Learning from Observation with Model Misspecification
Luca Viano, Yu-Ting Huang, Parameswaran Kamalaruban, Craig Innes, Subramanian Ramamoorthy, Adrian Weller
Imitation Learning Robust Learning Robust Reinforcement Learning Model Misspecification Observation Centric Adversarial Imitation Generative Adversarial Imitation Learning

January 21, 2022

Deep Reinforcement Learning with Spiking Q-learning
Ding Chen, Peixi Peng, Tiejun Huang, Yonghong Tian
Deep Reinforcement Learning Neuromorphic Hardware Deep Q Network Robust Reinforcement Learning

December 2, 2021

Sample Complexity of Robust Reinforcement Learning with a Generative Model
Kishan Panaganti, Dileep Kalathil
Generative Modeling Sample Complexity Robust Policy Robust Reinforcement Learning Optimal Robust Policy Robust Markov Decision