paper-with-me

홈 › Papers

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

2023-07-27 · Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, Tony Wang, Samuel Marks, Charbel-Raphaël Segerie, Micah Carroll, Andi Peng, Phillip Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan, Max Nadeau, Eric J. Michaud, Jacob Pfau, Dmitrii Krasheninnikov, Xin Chen, Lauro Langosco, Peter Hase, Erdem Biyik, Anca Dragan, David Krueger, Dorsa Sadigh, Dylan Hadfield-Menell

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large language models (LLMs). Despite this popularity, there has been relatively little public work systematizing its flaws. In this paper, we (1) survey open problems and fundamental limitations of RLHF and related methods; (2) overview techniques to understand, improve, and complement RLHF in practice; and (3) propose auditing and disclosure standards to improve societal oversight of RLHF systems. Our work emphasizes the limitations of RLHF and highlights the importance of a multi-faceted approach to the development of safer AI systems.

📄 PDF Abstract BibTeX arXiv:2307.15217

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey

2021-09-28 · Amjad Yousef Majid, Serge Saaybi, Tomas van Rietbergen, Vincent Francois-Lavet 외

Deep Reinforcement Learning (DRL) and Evolution Strategies (ESs) have surpassed human-level control in many sequential decision-making problems, yet many open challenges still exist. To get insights into the strengths an…

Decision MakingDeep Reinforcement Learningreinforcement-learningReinforcement Learning+3

Understanding Human Intelligence through Human Limitations

2020-09-29 · Thomas L. Griffiths

Recent progress in artificial intelligence provides the opportunity to ask the question of what is unique about human intelligence, but with a new comparison class. I argue that we can understand human intelligence, and …

Towards Human-level Dexterity via Robot Learning

2025-07-12 · Gagan Khandate arxiv

Dexterous intelligence -- the ability to perform complex interactions with multi-fingered hands -- is a pinnacle of human physical intelligence and emergent higher-order cognitive skills. However, contrary to Moravec's p…

Reinforcement Learning

Evolutionary Deep Reinforcement Learning Using Elite Buffer: A Novel Approach Towards DRL Combined with EA in Continuous Control Tasks

2022-09-18 · Marzieh Sadat Esmaeeli, Hamed Malek

Despite the numerous applications and success of deep reinforcement learning in many control tasks, it still suffers from many crucial problems and limitations, including temporal credit assignment with sparse reward, ab…

continuous-controlContinuous ControlDeep Reinforcement LearningEvolutionary Algorithms+3

On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures

2025-01-03 · Ming Yin, Mengdi Wang, Yu-Xiang Wang

This article reviews the recent advances on the statistical foundation of reinforcement learning (RL) in the offline and low-adaptive settings. We will start by arguing why offline RL is the appropriate model for almost …

Offline RLReinforcement Learning (RL)