paper-with-me

홈 › Papers

The Benefits of Coarse Preferences

2022-01-25 · Joseph Y. Halpern, Yuval Heller, Eyal Winter

We study the strategic advantages of coarsening one's utility by clustering nearby payoffs together (i.e., classifying them the same way). Our solution concept, coarse-utility equilibrium (CUE) requires that (1) each player maximizes her coarse utility, given the opponent's strategy, and (2) the classifications form best replies to one another. We characterize CUEs in various games. In particular, we show that there is a qualitative difference between CUEs in which only one of the players clusters payoffs, and those in which all players cluster their payoffs, and that the latter type induce players to treat co-players better than in Nash equilibria in the large class of games with monotone externalities.

📄 PDF Abstract BibTeX arXiv:2201.10141

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Similar Papers 제목 키워드 기반

Fast and Robust Rank Aggregation against Model Misspecification

2019-05-29 · Yuangang Pan, WeiJie Chen, Gang Niu, Ivor W. Tsang 외

In rank aggregation (RA), a collection of preferences from different users are summarized into a total order under the assumption of homogeneity of users. Model misspecification in RA arises since the homogeneity assumpt…

Bayesian Inferencemodel

Learning Correlated Reward Models: Statistical Barriers and Opportunities

2025-10-17 · Yeshwanth Cherapanamjeri, Constantinos Daskalakis, Gabriele Farina, Sobhan Mohammadpour arxiv

Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learning from Human Feedback (RLHF). However, a crucial shortcoming of many of…

Reinforcement Learning

Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation

2024-06-24 · Katherine M. Collins, Najoung Kim, Yonatan Bitton, Verena Rieser 외

Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively e…

Image GenerationText to Image GenerationText-to-Image Generation

Can We Perform Online RL for Image Editing without Editing Rewards?

2026-08-24 · Qichao Ma, Jikang Cheng, Ling Liang, Zhaofei Yu 외 arxiv

Reinforcement learning (RL) enables direct preference optimization for image editing through editing-specific rewards, which remain less developed due to costly triplet supervision and complex task-dependent calibration.…

Reinforcement LearningImage Editing

Rethinking IDE Customization for Enhanced HAX: A Hyperdimensional Perspective

2025-01-05 · Roham Koohestani, Maliheh Izadi

As Integrated Development Environments (IDEs) increasingly integrate Artificial Intelligence, Software Engineering faces both benefits like productivity gains and challenges like mismatched user preferences. We propose H…