大模型对齐与安全 - arXivDaily 专题

2106.09110 2021-07-20 cs.LG cs.RO cs.SY eess.SY 57%

Safe Reinforcement Learning Using Advantage-Based Intervention

Nolan Wagener, Byron Boots, Ching-An Cheng

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments Appearing in ICML 2021. 29 pages, 8 figures

2107.07413 2021-07-16 cs.RO cs.AI 57%

High-level Decisions from a Safe Maneuver Catalog with Reinforcement Learning for Safe and Cooperative Automated Merging

Danial Kamran, Yu Ren, Martin Lauer

专题命中安全训练：safety(abstract)；分类 cs.AI

1902.04118 2021-07-14 cs.LG cs.NE cs.PF stat.ML 57%

WiseMove: A Framework for Safe Deep Reinforcement Learning for Autonomous Driving

Jaeyoung Lee, Aravind Balakrishnan, Ashish Gaurav, Krzysztof Czarnecki, Sean Sedwards

专题命中安全训练：safety(abstract)；分类 cs.LG

Journal ref International Conference on Quantitative Evaluation of Systems (QEST 2019)

2107.03896 2021-07-09 cs.CY 57%

AI and the future of pharmaceutical research

Adam Zielinski

专题命中安全训练：safety(abstract)；分类 cs.CY

Comments 38 pages

2105.03052 2021-06-15 cs.MA cs.AI 57%

Informational Design of Dynamic Multi-Agent System

Tao Zhang, Quanyan Zhu

专题命中安全训练：alignment(abstract)；分类 cs.AI

Comments arXiv admin note: substantial text overlap with arXiv:2102.07152

2105.04196 2021-05-11 eess.SP cs.LG cs.MA 57%

AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning

Mohammad Parvini, Mohammad Reza Javan, Nader Mokari, Bijan Abbasi, Eduard A. Jorswieck

专题命中安全训练：safety(abstract)；分类 cs.LG

2105.00333 2021-05-04 cs.LG 57%

AI-enabled Efficient and Safe Food Supply Chain

Ilianna Kollia, Jack Stevenson, Stefanos Kollias

专题命中安全训练：safety(abstract)；分类 cs.LG

2104.11691 2021-04-26 cs.CV cs.CR cs.LG 57%

Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities

Julia Rosenzweig, Joachim Sicking, Sebastian Houben, Michael Mock, Maram Akila

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments Under IEEE Copyright; accepted at the SAIAD (Safe Artificial Intelligence for Automated Driving) Workshop at CVPR 2021

2104.08994 2021-04-20 cs.CR cs.AI cs.GT 57%

Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense

Ashutosh Dutta, Ehab Al-Shaer, Samrat Chatterjee

专题命中安全训练：safety(abstract)；分类 cs.AI

Comments 11 pages

2101.05436 2021-04-20 cs.MA cs.AI cs.SY eess.SY 57%

Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates

Zengyi Qin, Kaiqing Zhang, Yuxiao Chen, Jingkai Chen, Chuchu Fan

专题命中安全训练：safety(abstract)；分类 cs.AI

Comments Published at ICLR 2021

2104.06353 2021-04-14 cs.LG eess.SP 57%

Real-time Forecast Models for TBM Load Parameters Based on Machine Learning Methods

Xianjie Gao, Xueguan Song, Maolin Shi, Chao Zhang, Hongwei Zhang

专题命中安全训练：safety(abstract)；分类 cs.LG

2008.07081 2021-03-24 cs.LG cs.RO stat.ML 57%

MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation

Xiaoyi Chen, Pratik Chaudhari

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments Code available at https://github.com/sherrychen1120/MIDAS. To be presented at IEEE International Conference on Robotics and Automation (ICRA), 2021

2003.00613 2021-03-24 cs.AI cs.SY eess.SY 57%

How Do We Move: Modeling Human Movement with System Dynamics

Hua Wei, Dongkuan Xu, Junjie Liang, Zhenhui Li

专题命中安全训练：safety(abstract)；分类 cs.AI

Comments Accepted by AAAI 2021, Appendices included. 12 pages, 8 figures. in Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI'21), Feb 2021

2012.13681 2021-03-15 cs.RO cs.CV cs.LG 57%

Improving the Generalization of End-to-End Driving through Procedural Generation

Quanyi Li, Zhenghao Peng, Qihang Zhang, Chunxiao Liu, Bolei Zhou

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments Website: https://decisionforce.github.io/pgdrive

2103.06602 2021-03-12 cs.AI 57%

Symbolic Reinforcement Learning for Safe RAN Control

Alexandros Nikou, Anusha Mujumdar, Marin Orlic, Aneta Vulgarakis Feljan

专题命中安全训练：safety(abstract)；分类 cs.AI

Comments The paper has been accepted to be presented in 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), May 3-7, London, UK (demo track)

2101.00191 2021-03-12 cs.NI cs.LG 57%

Dynamic Federated Learning-Based Economic Framework for Internet-of-Vehicles

Yuris Mulya Saputra, Dinh Thai Hoang, Diep N. Nguyen, Le-Nam Tran, Shimin Gong, Eryk Dutkiewicz

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments 18 pages, 12 figures, submitted to an IEEE journal

2103.04811 2021-03-09 cs.CY 57%

A Framework for Enabling Safe and Resilient Food Factories for the Public Feeding Programs

Nataraj Kuntagod, Sanjay Podder, Satya Sai Srinivas Abbabathula, Venkatesh Subramanian, Giju Mathew, Suresh Kumar Mani

专题命中安全训练：safety(abstract)；分类 cs.CY

Comments 4 pages, 3 figures. To appear ICSE Workshop on Software Engineering for Healthcare, June 3, 2021, virtual

2005.03898 2021-02-09 cs.AI cs.NE cs.SE 57%

Synthesizing Safe Policies under Probabilistic Constraints with Reinforcement Learning and Bayesian Model Checking

Lenz Belzner, Martin Wirsing

专题命中安全训练：safety(abstract)；分类 cs.AI

2101.11196 2021-02-03 cs.LG cs.FL 57%

Safe Multi-Agent Reinforcement Learning via Shielding

Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato, Rüdiger Ehlers, Ufuk Topcu, Lu Feng

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments 8 pages, 11 figures and 2 tables, to be published in AAMAS 2021

2007.00544 2021-01-28 cs.LG cs.IT cs.RO eess.SP math.IT stat.ML 57%

UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning Approach

Harald Bayerlein, Mirco Theile, Marco Caccamo, David Gesbert

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments Code available under https://github.com/hbayerlein/uav_data_harvesting, IEEE Global Communications Conference (GLOBECOM) 2020

2101.08153 2021-01-25 cs.AI 57%

Shielding Atari Games with Bounded Prescience

Mirco Giacobbe, Mohammadhosein Hasanbeig, Daniel Kroening, Hjalmar Wijk

专题命中安全训练：safety(abstract)；分类 cs.AI

Comments To appear at AAMAS 2021

2006.12917 2021-01-14 cs.LG stat.ML 57%

Show me the Way: Intrinsic Motivation from Demonstrations

Léonard Hussenot, Robert Dadashi, Matthieu Geist, Olivier Pietquin

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments AAMAS 2021

2101.02082 2021-01-07 cs.AI cs.HC 57%

Artificial Intelligence Methods in In-Cabin Use Cases: A Survey

Yao Rong, Chao Han, Christian Hellert, Antje Loyal, Enkelejda Kasneci

专题命中安全训练：safety(abstract)；分类 cs.AI

Comments 11 pages, 3 figures, 3 tables

2101.01251 2021-01-06 cs.LG 57%

Robust Maximum Entropy Behavior Cloning

Mostafa Hussein, Brendan Crowe, Marek Petrik, Momotaz Begum

专题命中安全训练：trustworthy(abstract)；分类 cs.LG

Comments NeurIPS 2020 3rd Robot Learning Workshop: Grounding Machine Learning Development in the Real World

2101.00531 2021-01-05 cs.LG 57%

Context-Aware Safe Reinforcement Learning for Non-Stationary Environments

Baiming Chen, Zuxin Liu, Jiacheng Zhu, Mengdi Xu, Wenhao Ding, Ding Zhao

专题命中安全训练：safety(abstract)；分类 cs.LG

2012.03681 2020-12-08 cs.CV cs.AI 57%

Roof fall hazard detection with convolutional neural networks using transfer learning

Ergin Isleyen, Sebnem Duzgun, McKell R. Carter

专题命中安全训练：safety(abstract)；分类 cs.AI

2006.03947 2020-11-24 eess.SY cs.LG cs.SY stat.ML 57%

Neural Lyapunov Redesign

Arash Mehrjou, Mohammad Ghavamzadeh, Bernhard Schölkopf

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments 27 pages

2003.00534 2020-10-27 cs.LG math.OC stat.ML 57%

Provably Efficient Safe Exploration via Primal-Dual Policy Optimization

Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo R. Jovanović

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments 44 pages. We have revised the linear MDP assumption and fixed a bug in our previous proofs

2010.01722 2020-10-06 eess.SY cs.LG cs.SY 57%

Deep Reinforcement Learning for Collaborative Edge Computing in Vehicular Networks

Mushu Li, Jie Gao, Lian Zhao, Xuemin Shen

专题命中安全训练：safety(abstract)；分类 cs.LG

Comments 31 pages, single column, 12 figures. Accepted in IEEE Transactions on Cognitive Communications and Networking

2002.05502 2020-10-01 cs.LG stat.ML 57%

Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic

Yangang Ren, Jingliang Duan, Shengbo Eben Li, Yang Guan, Qi Sun

专题命中安全训练：safety(abstract)；分类 cs.LG

1. 安全训练 3281 篇

Safe Reinforcement Learning Using Advantage-Based Intervention

High-level Decisions from a Safe Maneuver Catalog with Reinforcement Learning for Safe and Cooperative Automated Merging

WiseMove: A Framework for Safe Deep Reinforcement Learning for Autonomous Driving

AI and the future of pharmaceutical research

Informational Design of Dynamic Multi-Agent System

AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning

AI-enabled Efficient and Safe Food Supply Chain

Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities

Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense

Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates

Real-time Forecast Models for TBM Load Parameters Based on Machine Learning Methods

MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation

How Do We Move: Modeling Human Movement with System Dynamics

Improving the Generalization of End-to-End Driving through Procedural Generation

Symbolic Reinforcement Learning for Safe RAN Control

Dynamic Federated Learning-Based Economic Framework for Internet-of-Vehicles

A Framework for Enabling Safe and Resilient Food Factories for the Public Feeding Programs

Synthesizing Safe Policies under Probabilistic Constraints with Reinforcement Learning and Bayesian Model Checking

Safe Multi-Agent Reinforcement Learning via Shielding

UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning Approach

Shielding Atari Games with Bounded Prescience

Show me the Way: Intrinsic Motivation from Demonstrations

Artificial Intelligence Methods in In-Cabin Use Cases: A Survey

Robust Maximum Entropy Behavior Cloning

Context-Aware Safe Reinforcement Learning for Non-Stationary Environments

Roof fall hazard detection with convolutional neural networks using transfer learning

Neural Lyapunov Redesign

Provably Efficient Safe Exploration via Primal-Dual Policy Optimization

Deep Reinforcement Learning for Collaborative Edge Computing in Vehicular Networks

Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic