Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

2022-09-16 · Mengdi Xu, Zuxin Liu, Peide Huang, Wenhao Ding, Zhepeng Cen, Bo Li, Ding Zhao

A trustworthy reinforcement learning algorithm should be competent in solving challenging real-world problems, including {robustly} handling uncertainties, satisfying {safety} constraints to avoid catastrophic failures, and {generalizing} to unseen scenarios during deployments. This study aims to overview these main perspectives of trustworthy reinforcement learning considering its intrinsic vulnerabilities on robustness, safety, and generalizability. In particular, we give rigorous formulations, categorize corresponding methodologies, and discuss benchmarks for each perspective. Moreover, we provide an outlook section to spur promising future directions with a brief discussion on extrinsic vulnerabilities considering human feedback. We hope this survey could bring together separate threads of studies together in a unified framework and promote the trustworthiness of reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2209.08025

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Towards Optimal Adversarial Robust Reinforcement Learning with Infinity Measurement Error

2025-02-23 · Haoran Li, ZiCheng Zhang, Wang Luo, Congying Han 외

Ensuring the robustness of deep reinforcement learning (DRL) agents against adversarial attacks is critical for their trustworthy deployment. Recent research highlights the challenges of achieving state-adversarial robus…

Adversarial Robustness Deep Reinforcement Learning reinforcement-learning Reinforcement Learning

A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacy

2023-02-21 · Yifei Zhang, Dun Zeng, Jinglong Luo, Zenglin Xu 외

Trustworthy artificial intelligence (AI) technology has revolutionized daily life and greatly benefited human society. Among various AI technologies, Federated Learning (FL) stands out as a promising solution for diverse…

Drug Discovery Federated Learning

Assessing Adversarial Robustness of Large Language Models: An Empirical Study

2024-05-04 · Zeyu Yang, Zhao Meng, Xiaochen Zheng, Roger Wattenhofer

Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes …

Adversarial Robustness text-classification Text Classification

Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbations

2024-12-25 · Shingo Ayabe, Takuto Otomo, Hiroshi Kera, Kazuhiko Kawamoto

Offline reinforcement learning, which learns solely from datasets without environmental interaction, has gained attention. This approach, similar to traditional online deep reinforcement learning, is particularly promisi…

Deep Reinforcement Learning OpenAI Gym reinforcement-learning Reinforcement Learning

RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies

2019-06-03 · Vahid Behzadan, William Hsu

This paper investigates the resilience and robustness of Deep Reinforcement Learning (DRL) policies to adversarial perturbations in the state space. We first present an approach for the disentanglement of vulnerabilities…

Benchmarking Deep Reinforcement Learning Disentanglement reinforcement-learning+4