# Adaptive Adversarial Training for Meta Reinforcement Learning

arXiv: https://arxiv.org/abs/2104.13302 · HTML: https://mlsanity.com/paper/2104.13302/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 27 Apr 2021.

## Builds on (most cited first, 21 of 21)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [Tactics of Adversarial Attack on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1703.06748/) (2017)
- [Robust Deep Reinforcement Learning with Adversarial Attacks](https://mlsanity.com/paper/1712.03632/) (2017)
- [Delving into adversarial attacks on deep policies](https://mlsanity.com/paper/1705.06452/) (2017)
- [ProMP: Proximal Meta-Policy Search](https://mlsanity.com/paper/1810.06784/) (2018)
- [Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning](https://mlsanity.com/paper/2003.12909/) (2020)
- [Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations](https://mlsanity.com/paper/1308.3513/) (2013)
- [Meta Reinforcement Learning with Latent Variable Gaussian Processes](https://mlsanity.com/paper/1803.07551/) (2018)
- [Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling](https://mlsanity.com/paper/2006.07178/) (2020)
- [Adversarial Meta-Learning](https://mlsanity.com/paper/1806.03316/) (2018)
- [Adversarially Robust Few-Shot Learning: A Meta-Learning Approach](https://mlsanity.com/paper/1910.00982/) (2019)
- [Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning](https://mlsanity.com/paper/2009.00402/) (2020)
- [Meta Dropout: Learning to Perturb Features for Generalization](https://mlsanity.com/paper/1905.12914/) (2019)

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

- [Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey](https://mlsanity.com/paper/2303.06302/) (2023)

## Abstract (arXiv)

Meta Reinforcement Learning (MRL) enables an agent to learn from a limited number of past trajectories and extrapolate to a new task. In this paper, we attempt to improve the robustness of MRL. We build upon model-agnostic meta-learning (MAML) and propose a novel method to generate adversarial samples for MRL by using Generative Adversarial Network (GAN). That allows us to enhance the robustness of MRL to adversal attacks by leveraging these attacks during meta training process.