MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning

[免费ChatGPT] [DeepSeek可用网址] [PDF] arxiv.org

SHARPIE: A Modular Framework for Reinforcement Learning and Human-AI Interaction Experiments

H Aydın, K Dubois-Godin, LG Braz, F Hengst… - arxiv preprint arxiv …, 2025 - arxiv.org
Reinforcement learning (RL) offers a general approach for modeling and training AI agents,
including human-AI interaction scenarios. In this paper, we propose SHARPIE (Shared …
Išsaugoti Cituoti Susiję straipsniai Visos 3 versijos HTML kopija
[免费ChatGPT] [DeepSeek可用网址] [PDF] openreview.net

From Conflicts to Convergence: A Zeroth-order Method for Multi-Objective Learning

X Liu, X Yuan, H Chen, B Gu, H **ong, Z Li, X Zhang - openreview.net
Multi-objective learning (MOL) is a popular paradigm for learning problems under multiple
criteria, where various dynamic weighting algorithms (eg, MGDA and MODO) have been …
Išsaugoti Cituoti Susiję straipsniai HTML kopija