paper-with-me

홈 › Papers

Advantage Alignment Algorithms

2024-06-20 · Juan Agustin Duque, Milad Aghajohari, Tim Cooijmans, Razvan Ciuca, Tianyu Zhang, Gauthier Gidel, Aaron Courville

Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often optimize their individual objective, leading to conflicts, particularly in general-sum games where naive reinforcement learning agents empirically converge to Pareto-suboptimal Nash equilibria. To address this issue, opponent shaping has emerged as a paradigm for finding socially beneficial equilibria in general-sum games. In this work, we introduce Advantage Alignment, a family of algorithms derived from first principles that perform opponent shaping efficiently and intuitively. We achieve this by aligning the advantages of interacting agents, increasing the probability of mutually beneficial actions when their interaction has been positive. We prove that existing opponent shaping methods implicitly perform Advantage Alignment. Compared to these methods, Advantage Alignment simplifies the mathematical formulation of opponent shaping, reduces the computational burden and extends to continuous action domains. We demonstrate the effectiveness of our algorithms across a range of social dilemmas, achieving state-of-the-art cooperation and robustness against exploitation.

📄 PDF Abstract BibTeX arXiv:2406.14662

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous VehiclesDecision MakingLanguage ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Face Alignment In-the-Wild: A Survey

2016-08-15 · Xin Jin, Xiaoyang Tan

Over the last two decades, face alignment or localizing fiducial facial points has received increasing attention owing to its comprehensive applications in automatic face analysis. However, such a task has proven extreme…

Face AlignmentRobust Face AlignmentSurvey

Understanding the performance gap between online and offline alignment algorithms

2024-05-14 · Yunhao Tang, Daniel Zhaohan Guo, Zeyu Zheng, Daniele Calandriello 외

Reinforcement learning from human feedback (RLHF) is the canonical framework for large language model alignment. However, rising popularity in offline alignment algorithms challenge the need for on-policy sampling in RLH…

Language ModellingLarge Language Model

Efficient and Accurate Face Alignment by Global Regression and Cascaded Local Refinement

2019-06-16 · CVPR 2019 2019 6 · Jinzhan Su, Zhe Wang, Chunyuan Liao, Haibin Ling

Despite great advances witnessed on facial image alignment in recent years, high accuracy high speed face alignment algorithms still have rooms to improve especially for applications where computation resources are limit…

Face Alignmentregression

Stepwise Alignment for Constrained Language Model Policy Optimization

2024-04-17 · Akifumi Wachi, Thien Q. Tran, Rei Sato, Takumi Tanabe 외

Safety and trustworthiness are indispensable requirements for real-world applications of AI systems using large language models (LLMs). This paper formulates human value alignment as an optimization problem of the langua…

Computational EfficiencyLanguage ModelingLanguage Modellingmodel

A recursive robust filtering approach for 3D registration

2021-10-28 · Abdenour Amamra, Nabil Aouf, Dowling Stuart, Mark Richardson

This work presents a new recursive robust filtering approach for feature-based 3D registration. Unlike the common state-of-the-art alignment algorithms, the proposed method has four advantages that have not yet occurred …