Sample-Efficient Reinforcement Learning From Human Feedback via Information-Directed Sampling

Qi Han; Haochen Yang; Qiaosheng Zhang; Zhuoran Yang

doi:10.1109/tit.2025.3598296

ScienceGate Book Chapters

JOURNAL ARTICLE

Sample-Efficient Reinforcement Learning From Human Feedback via Information-Directed Sampling

Qi Han Haochen Yang Qiaosheng Zhang Zhuoran Yang

Year: 2025 Journal: IEEE Transactions on Information Theory Vol: 71 (10)Pages: 7942-7958 Publisher: Institute of Electrical and Electronics Engineers

DOI: 10.1109/tit.2025.3598296

Get Full-Text PDF Get Analytical Report

Keywords:

Reinforcement learning Computer science Sample (material) Sampling (signal processing) Artificial intelligence Machine learning Statistics Mathematics Computer vision

Metrics

Cited By

0.00

FWCI (Field Weighted Citation Impact)

Refs

0.13

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Topics

Reinforcement Learning in Robotics

Physical Sciences → Computer Science → Artificial Intelligence

Distributed Sensor Networks and Detection Algorithms

Physical Sciences → Computer Science → Computer Networks and Communications

Neural Networks and Applications

Physical Sciences → Computer Science → Artificial Intelligence

Sample-Efficient Reinforcement Learning From Human Feedback via Information-Directed Sampling

Metrics

Topics

Related Documents

Sample and Feedback Efficient Hierarchical Reinforcement Learning from Human Preferences

Provably efficient information-directed sampling algorithms for multi-agent reinforcement learning

Efficient and Robust Reinforcement Learning from Human Feedback

Sample-efficient deep reinforcement learning with directed associative graph

Sample Efficient Reinforcement Learning with Double Importance Sampling Weight Clipping