# Adversarial Reinforcement Learning: A Duality-Based Approach To Solving Optimal Control Problems

arXiv: https://arxiv.org/abs/2506.00801 · HTML: https://mlsanity.com/paper/2506.00801/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 8 of 8)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Solving high-dimensional partial differential equations using deep learning](https://mlsanity.com/paper/1707.02568/) (2017)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Deep Hedging](https://mlsanity.com/paper/1802.03042/) (2018)
- [Deep Learning Approximation for Stochastic Control Problems](https://mlsanity.com/paper/1611.07422/) (2016)
- [Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis](https://mlsanity.com/paper/1812.04300/) (2018)
- [Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications](https://mlsanity.com/paper/1812.05916/) (2018)
- [Deep Empirical Risk Minimization in finance: looking into the future](https://mlsanity.com/paper/2011.09349/) (2020)

## Built on by (most cited first, 1 of 1)

- [Dual Approaches to Stochastic Control via SPDEs and the Pathwise Hopf Formula](https://mlsanity.com/paper/2604.08155/) (2026)

## Abstract (arXiv)

We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between policies and adversarial penalties, enforcing non-anticipativity while preserving optimality. Numerical experiments demonstrate ADRL's superior performance to yield tight dual gaps. Our results highlight the potential of ADRL as a robust computational framework for high-dimensional stochastic control in simulation-based optimization contexts.