# Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

arXiv: https://arxiv.org/abs/2307.12062 · HTML: https://mlsanity.com/paper/2307.12062/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 52 of its 79 references that are in the map.
- First posted on arXiv 22 Jul 2023.

## Builds on (most cited first, 30 of 52)

- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning](https://mlsanity.com/paper/1711.00832/) (2017)
- [Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations](https://mlsanity.com/paper/2003.08938/) (2020)
- [DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker](https://mlsanity.com/paper/1701.01724/) (2017)
- [Adversarial Policies: Attacking Deep Reinforcement Learning](https://mlsanity.com/paper/1905.10615/) (2019)
- [Action Robust Reinforcement Learning and Applications in Continuous Control](https://mlsanity.com/paper/1901.09184/) (2019)
- [Deep Reinforcement Learning from Self-Play in Imperfect-Information Games](https://mlsanity.com/paper/1603.01121/) (2016)
- [Robust Deep Reinforcement Learning with Adversarial Attacks](https://mlsanity.com/paper/1712.03632/) (2017)
- [Robust Reinforcement Learning on State Observations with Learned Optimal Adversary](https://mlsanity.com/paper/2101.08452/) (2021)
- [Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning](https://mlsanity.com/paper/2206.15378/) (2022)
- [Combining Deep Reinforcement Learning and Search for Imperfect-Information Games](https://mlsanity.com/paper/2007.13544/) (2020)
- [Delving into adversarial attacks on deep policies](https://mlsanity.com/paper/1705.06452/) (2017)
- [Deep Counterfactual Regret Minimization](https://mlsanity.com/paper/1811.00164/) (2018)
- [Robust Reinforcement Learning for Continuous Control with Model Misspecification](https://mlsanity.com/paper/1906.07516/) (2019)
- [Robust Deep Reinforcement Learning through Adversarial Loss](https://mlsanity.com/paper/2008.01976/) (2020)
- [Safe Reinforcement Learning by Imagining the Near Future](https://mlsanity.com/paper/2202.07789/) (2022)
- [Robust Reinforcement Learning using Adversarial Populations](https://mlsanity.com/paper/2008.01825/) (2020)
- [DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning](https://mlsanity.com/paper/2106.06135/) (2021)
- [A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games](https://mlsanity.com/paper/2206.05825/) (2022)
- [From Poincar'e Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization](https://mlsanity.com/paper/2002.08456/) (2020)
- [Suphx: Mastering Mahjong with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.13590/) (2020)
- [Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL](https://mlsanity.com/paper/2106.05087/) (2021)
- [A Generalized Training Approach for Multiagent Learning](https://mlsanity.com/paper/1909.12823/) (2019)
- [Certified Adversarial Robustness for Deep Reinforcement Learning](https://mlsanity.com/paper/1910.12908/) (2019)
- [Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games](https://mlsanity.com/paper/2006.08555/) (2020)
- [Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning](https://mlsanity.com/paper/2303.02783/) (2023)
- [Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning](https://mlsanity.com/paper/2210.05927/) (2022)
- [Finding Friend and Foe in Multi-Agent Games](https://mlsanity.com/paper/1906.02330/) (2019)
- [CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing](https://mlsanity.com/paper/2106.09292/) (2021)

## Abstract (arXiv)

Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced independently across time. However, practical sources of uncertainty are usually coupled across time. We formally introduce temporally-coupled perturbations, presenting a novel challenge for existing robust RL methods. To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially observable two-player zero-sum game. By finding an approximate equilibrium within this game, GRAD optimizes for general robustness against temporally-coupled perturbations. Experiments on continuous control tasks demonstrate that, compared with prior methods, our approach achieves a higher degree of robustness to various types of attacks on different attack domains, both in settings with temporally-coupled perturbations and decoupled perturbations.