Paper Reading AI Learner

Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey

2024-03-01 10:16:46
Lucas Schott, Josephine Delas, Hatem Hajri, Elies Gherbi, Reda Yaich, Nora Boulahia-Cuppens, Frederic Cuppens, Sylvain Lamprier

Abstract

Deep Reinforcement Learning (DRL) is an approach for training autonomous agents across various complex environments. Despite its significant performance in well known environments, it remains susceptible to minor conditions variations, raising concerns about its reliability in real-world applications. To improve usability, DRL must demonstrate trustworthiness and robustness. A way to improve robustness of DRL to unknown changes in the conditions is through Adversarial Training, by training the agent against well suited adversarial attacks on the dynamics of the environment. Addressing this critical issue, our work presents an in-depth analysis of contemporary adversarial attack methodologies, systematically categorizing them and comparing their objectives and operational mechanisms. This classification offers a detailed insight into how adversarial attacks effectively act for evaluating the resilience of DRL agents, thereby paving the way for enhancing their robustness.

Abstract (translated)

深度强化学习(DRL)是一种训练各种复杂环境中自主行动的智能体的方法。尽管在著名环境中表现出色,但它仍然容易受到轻微条件变化的影响,这使得人们对它在现实应用中的可靠性产生担忧。为了提高可用性,DRL必须表现出可靠性、容错性。提高DRL对未知条件变化容错性的方法是通过对抗训练,通过训练智能体对抗适合环境动态的合适对抗攻击。为解决这一关键问题,我们的工作对当代攻击方法进行了深入分析,系统地分类并比较了它们的 objectives 和操作机制。这种分类提供了一个详细了解如何有效评估 DRL 代理的韧性的见解,为提高其韧性和可靠性铺平道路。

URL

https://arxiv.org/abs/2403.00420

PDF

https://arxiv.org/pdf/2403.00420.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot