工业4.0创新平台

Augmenting Reinforcement Learning with Human Feedback [英文]

页数：8 阅读：361 次 标签：人工智能学术论文强化学习 RLHF

Augmenting Reinforcement Learning with Human Feedback

W. Bradley Knox BRADKNOX@CS.UTEXAS.EDU

University of Texas at Austin, Department of Computer Science

更多

上传于 2023-02-13 11:53

Policy Shaping: Integrating Human Feedback with Reinforcement Learning [英文]

页数：9 阅读：283 次 标签：人工智能学术论文强化学习 RLHF

Policy Shaping: Integrating Human Feedback with Reinforcement Learning

Shane Griffith, Kaushik Subramanian, Jonathan Scholz, Charles L. Isbell, and Andrea Thomaz

College of Computing

更多

上传于 2023-02-13 11:53

Deep Reinforcement Learning from Human Preferences [英文]

页数：9 阅读：288 次 标签：人工智能学术论文强化学习 RLHF

Deep Reinforcement Learning

from Human Preferences

Paul F Christiano

更多

上传于 2023-02-13 11:53

Reinforcement Learning with Human Teachers: Evidence of Feedback and Guidance with Implications for Learning Performance [英文]

页数：6 阅读：252 次 标签：人工智能学术论文强化学习 RLHF

Reinforcement Learning with Human Teachers: Evidence of Feedback and Guidance with Implications for Learning Performance

Andrea L. Thomaz and Cynthia Breazeal

MIT Media Lab

更多

上传于 2023-02-13 11:53

The Expertise Problem: Learning from Specialized Feedback [英文]

页数：10 阅读：287 次 标签：人工智能学术论文强化学习 RLHF

The Expertise Problem:

Learning from Specialized Feedback

Oliver Daniels-Koch

更多

上传于 2023-02-13 11:53

Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning [英文]

页数：12 阅读：280 次 标签：人工智能学术论文强化学习 RLHF

Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning

Julia Kreutzer1 and Joshua Uyheng3 and Stefan Riezler1;2

1Computational Linguistics & 2IWR, Heidelberg University, Germany

更多

上传于 2023-02-13 11:53

Reinforcement Learning with Human Teachers: Understanding How People Want to Teach Robots [英文]

页数：6 阅读：273 次 标签：人工智能学术论文强化学习 RLHF

Reinforcement Learning with Human Teachers:

Understanding How People Want to Teach Robots

Andrea L. Thomaz, Guy Hoffman, Cynthia Breazeal

上传于 2023-02-13 11:53

On Agent Incentives to Manipulate Human Feedback in Multi-Agent Reward Learning Scenarios [英文]

页数：3 阅读：288 次 标签：人工智能学术论文强化学习 RLHF

On Agent Incentives to Manipulate Human Feedback in

Multi-Agent Reward Learning Scenarios

Extended Abstract

更多

上传于 2023-02-13 11:53