Concrete Problems in AI Safety

21 June 2016

Papers citing "Concrete Problems in AI Safety"

50 / 487 papers shown

Title
Model-Free Risk-Sensitive Reinforcement Learning Grégoire Delétang Jordi Grau-Moya M. Kunesch Tim Genewein Rob Brekelmans Shane Legg Pedro A. Ortega OOD 13 9 0 04 Nov 2021
MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks Nicholas Hoernle Rafael-Michael Karampatsis Vaishak Belle Y. Gal 27 59 0 02 Nov 2021
GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL Sumedh Anand Sontakke Stephen Iota Zizhao Hu Arash Mehrjou Laurent Itti Bernhard Schölkopf OODD 20 2 0 29 Oct 2021
What Do We Mean by Generalization in Federated Learning? Honglin Yuan Warren Morningstar Lin Ning K. Singhal OOD FedML 46 71 0 27 Oct 2021
Generalized Out-of-Distribution Detection: A Survey Jingkang Yang Kaiyang Zhou Yixuan Li Ziwei Liu 193 881 0 21 Oct 2021
On games and simulators as a platform for development of artificial intelligence for command and control Vinicius G. Goecks Nicholas R. Waytowich Derrik E. Asher Song Jun Park Mark R. Mittrick ... Anne Logie Mark S. Dennison T. Trout Priya Narayanan Alexander Kott 41 26 0 21 Oct 2021
A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays Leonardo Ravaglia Manuele Rusci D. Nadalini Alessandro Capotondi Francesco Conti Luca Benini BDL 41 64 0 20 Oct 2021
Natural Attribute-based Shift Detection Jeonghoon Park Jimin Hong Radhika Dua Daehoon Gwak Yixuan Li Jaegul Choo Edward Choi OOD 25 3 0 18 Oct 2021
Multi-Agent Constrained Policy Optimisation Shangding Gu J. Kuba Munning Wen Ruiqing Chen Ziyan Wang Zheng Tian Jun Wang Alois Knoll Yaodong Yang 98 49 0 06 Oct 2021
Trustworthy AI: From Principles to Practices Bo-wen Li Peng Qi Bo Liu Shuai Di Jingen Liu Jiquan Pei Jinfeng Yi Bowen Zhou 119 357 0 04 Oct 2021
BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining Weizhe Hua Yichi Zhang Chuan Guo Zhiru Zhang G. E. Suh OOD 39 15 0 29 Sep 2021
Recursively Summarizing Books with Human Feedback Jeff Wu Long Ouyang Daniel M. Ziegler Nissan Stiennon Ryan J. Lowe Jan Leike Paul Christiano ALM 40 296 0 22 Sep 2021
MPC-Friendly Commitments for Publicly Verifiable Covert Security Nitin Agrawal James Bell Adria Gascon Matt J. Kusner 28 4 0 15 Sep 2021
No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets Fahim Tajwar Ananya Kumar Sang Michael Xie Percy Liang OODD 27 21 0 12 Sep 2021
Robust fine-tuning of zero-shot models Mitchell Wortsman Gabriel Ilharco Jong Wook Kim Mike Li Simon Kornblith ... Raphael Gontijo-Lopes Hannaneh Hajishirzi Ali Farhadi Hongseok Namkoong Ludwig Schmidt VLM 71 697 0 04 Sep 2021
Evaluating Predictive Uncertainty under Distributional Shift on Dialogue Dataset Nyoungwoo Lee chaeHun Park Ho-Jin Choi 47 0 0 01 Sep 2021
NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models Myeongjun Jang Thomas Lukasiewicz 24 4 0 29 Aug 2021
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators Zhilin Zhao LongBing Cao Kun-Yu Lin 39 11 0 23 Aug 2021
Out-of-Distribution Detection Using Outlier Detection Methods Jan Diers Christian Pigorsch OODD 28 3 0 18 Aug 2021
A Framework for Understanding AI-Induced Field Change: How AI Technologies are Legitimized and Institutionalized B. Larsen 24 4 0 18 Aug 2021
Dealing with Distribution Mismatch in Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images: A Novel Approach Using Feature Densities Saul Calderon-Ramirez Shengxiang-Yang David Elizondo Armaghan Moemeni OOD 28 24 0 17 Aug 2021
Reimagining an autonomous vehicle Jeffrey Hawke E. Haibo Vijay Badrinarayanan Alex Kendall 46 11 0 12 Aug 2021
Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback Xiaofei Wang Kimin Lee Kourosh Hakhamaneshi Pieter Abbeel Michael Laskin 34 42 0 11 Aug 2021
Risk Averse Bayesian Reward Learning for Autonomous Navigation from Human Demonstration Christian Ellis Maggie B. Wigness J. Rogers Craig T. Lennon L. Fiondella 90 6 0 31 Jul 2021
Who's Afraid of Thomas Bayes? Erick Galinkin AAML 28 0 0 30 Jul 2021
Toward AI Assistants That Let Designers Design Sebastiaan De Peuter Antti Oulasvirta Samuel Kaski AI4CE 29 19 0 22 Jul 2021
Visual Adversarial Imitation Learning using Variational Models Rafael Rafailov Tianhe Yu Aravind Rajeswaran Chelsea Finn SSL 28 49 0 16 Jul 2021
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot Joel Z Leibo Edgar A. Duénez-Guzmán A. Vezhnevets J. Agapiou P. Sunehag Raphael Köster Jayd Matyas Charlie Beattie Igor Mordatch T. Graepel OffRL 58 104 0 14 Jul 2021
Online Adaptation to Label Distribution Shift Ruihan Wu Chuan Guo Yi-Hsun Su Kilian Q. Weinberger 21 47 0 09 Jul 2021
Physics-Guided Deep Learning for Dynamical Systems: A Survey Rui Wang Rose Yu AI4CE PINN 46 65 0 02 Jul 2021
Unsupervised Model Drift Estimation with Batch Normalization Statistics for Dataset Shift Detection and Model Selection Won-Jo Lee Seokhyun Byun Jooeun Kim Minje Park Kirill Chechil AI4TS 21 2 0 01 Jul 2021
Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits Wenshuo Guo Kumar Krishna Agrawal Aditya Grover Vidya Muthukumar A. Pananjady 16 8 0 28 Jun 2021
Ensembling Shift Detectors: an Extensive Empirical Evaluation Simona Maggio L. Dreyfus-Schmidt AI4TS 34 3 0 28 Jun 2021
Compositional Reinforcement Learning from Logical Specifications Kishor Jothimurugan Suguman Bansal Osbert Bastani Rajeev Alur CoGe 28 78 0 25 Jun 2021
Being a Bit Frequentist Improves Bayesian Neural Networks Agustinus Kristiadi Matthias Hein Philipp Hennig BDL UQCV 23 15 0 18 Jun 2021
A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection Jie Jessie Ren Stanislav Fort J. Liu Abhijit Guha Roy Shreyas Padhy Balaji Lakshminarayanan UQCV 33 219 0 16 Jun 2021
Safe Reinforcement Learning Using Advantage-Based Intervention Nolan Wagener Byron Boots Ching-An Cheng 34 52 0 16 Jun 2021
On-Policy Deep Reinforcement Learning for the Average-Reward Criterion Yiming Zhang Keith Ross OffRL 41 41 0 14 Jun 2021
Taxonomy of Machine Learning Safety: A Survey and Primer Sina Mohseni Haotao Wang Zhiding Yu Chaowei Xiao Zhangyang Wang J. Yadawa 31 31 0 09 Jun 2021
Definitions of intent suitable for algorithms Hal Ashton 13 18 0 08 Jun 2021
Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs Tao-Wen Liu Ruida Zhou D. Kalathil P. R. Kumar Chao Tian 42 78 0 04 Jun 2021
Goal Misgeneralization in Deep Reinforcement Learning L. Langosco Jack Koch Lee D. Sharkey J. Pfau Laurent Orseau David M. Krueger 30 78 0 28 May 2021
A Survey on Interactive Reinforcement Learning: Design Principles and Open Challenges Christian Arzate Cruz Takeo Igarashi OffRL 17 94 0 27 May 2021
Quantifying Uncertainty in Deep Spatiotemporal Forecasting Dongxian Wu Liyao (Mars) Gao X. Xiong Matteo Chinazzi Alessandro Vespignani Yi Ma Rose Yu AI4TS 16 68 0 25 May 2021
True Few-Shot Learning with Language Models Ethan Perez Douwe Kiela Kyunghyun Cho 21 428 0 24 May 2021
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence Wenhao Zhan Shicong Cen Baihe Huang Yuxin Chen Jason D. Lee Yuejie Chi 24 76 0 24 May 2021
Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs Lorena Qendro Sangwon Ha R. D. Jong Partha P. Maji AAML FedML MQ 21 7 0 13 May 2021
Intelligence and Unambitiousness Using Algorithmic Information Theory Michael K. Cohen Badri N. Vellambi Marcus Hutter 16 2 0 13 May 2021
Safety of the Intended Driving Behavior Using Rulebooks Anne-Sophie Collin Artur Bilka S. Pendleton R. D. Tebbens 6 25 0 10 May 2021
Software Engineering for AI-Based Systems: A Survey Silverio Martínez-Fernández Justus Bogner Xavier Franch Marc Oriol Julien Siebert Adam Trendowicz Anna Maria Vollmer Stefan Wagner 27 211 0 05 May 2021