This work studies heterogeneous Multi-Objective Reinforcement Learning (MORL), where objectives can differ sharply in temporal frequency. Such heterogeneity allows dense objectives to dominate learning, while sparse long-horizon rewards receive weak credit assignment, leading to poor sample efficiency. We propose a Parallel Reward Integration with Symmetry (PRISM) algorithm that enforces reflectional symmetry as an inductive bias in aligning reward channels. PRISM introduces ReSymNet, a theory-motivated model that reconciles temporal-frequency mismatches across objectives, using residual blocks to learn a scaled opportunity value that accelerates exploration while preserving the optimal policy. We also propose SymReg, a reflectional equivariance regulariser that enforces agent mirroring and constrains policy search to a reflection-equivariant subspace. This restriction provably reduces hypothesis complexity and improves generalisation. Across MuJoCo benchmarks, PRISM consistently outperforms both a sparse-reward baseline and an oracle trained with full dense rewards, improving Pareto coverage and distributional balance: it achieves hypervolume gains exceeding 100\% over the baseline and up to 32\% over the oracle. The code is at \href{https://github.com/EVIEHub/PRISM}{https://github.com/EVIEHub/PRISM}.
gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach
Institute for Applied Materials - Computational Materials Science (IAM - CMS), Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院应用材料研究所——计算材料科学方向(IAM-CMS));Intelligent Systems Research Group (ISRG), Karlsruhe University of Applied Sciences(卡尔斯鲁厄应用技术大学智能系统研究组(ISRG))
Center for Intelligent and Networked System (CFINS)(智能与网络化系统中心);Department of Automation(自动化系);Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心);Beijing Key Laboratory of Embodied Intelligence Systems(北京具身智能系统重点实验室);Tsinghua University(清华大学)
Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment
Institute of Innovation, Science and Sustainability(创新、科学与可持续发展研究所);Federation University Australia(澳大利亚联邦大学);Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);School of IT(信息技术学院);Deakin University(迪肯大学)
Reinforcement Learning for Testing Interdependent Requirements in Autonomous Vehicles: An Empirical Study
Simula Research Laboratory and University of Oslo(Simula研究实验室和奥斯陆大学);Mondragon University(蒙dragon大学);Simula Research Laboratory(Simula研究实验室);University of Oslo(奥斯陆大学)
PRISM: Recovering Instruction Sets from Language Model Activations
Center for Cybersecurity Systems & Networks, Amrita Vishwa Vidyapeetham(阿姆里塔·维什瓦·维迪亚佩瑟姆网络安全系统与网络中心);Microsoft(微软);Ben-Gurion University of the Negev(内盖夫本-古里安大学)
Dynamic Bicycle Dispatching of Dockless Public Bicycle-sharing Systems using Multi-objective Reinforcement Learning
Hunan University(湖南大学);State University of New York(纽约州立大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校);Agency for Science Technology and Research (A*STAR)(科学、技术与研究局(A*STAR));Institute for Infocomm Research(资讯通信研究院)
Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning
Federation University Australia(澳大利亚联邦大学);Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);University of Galway(高威大学);Deakin University(迪肯大学);Linköping University(林雪平大学);Universidade do Vale do Rio dos Sinos(南里约 dos Sinos大学);Vrije Universiteit Brussel(布鲁塞尔自由大学)
MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment
Department of Statistics, Rutgers University, New Brunswick, United States;Department of Computer Science, Rutgers University, New Brunswick, United States;College of Management of Technology, EPFL, Switzerland;Department of Computer Science, ETH Zurich, Switzerland
Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving
College of Automotive and Energy Engineering, Tongji University(同济大学汽车与能源工程学院);Department of Data and Systems Engineering, University of Hong Kong(香港大学数据与系统工程系)
Multi-Objective Reinforcement Learning for Energy-Efficient Industrial Control
Centre for Intelligent and Secure Industrial Automation(智能与安全工业自动化中心);Salzburg University of Applied Sciences(萨尔茨堡应用科学大学);Paris Lodron University of Salzburg(萨尔茨堡巴黎洛登大学);Kempten University of Applied Sciences(凯普滕应用科学大学)
提出多目标强化学习框架,通过复合奖励平衡 Quanser Aero 2 的俯仰跟踪与能耗,并分析能量惩罚权重及 Adam 优化器对 Pareto 最优性的影响。
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
University of Science and Technology of China(中国科学技术大学);Shanghai AI Laboratory(上海人工智能实验室);The Chinese University of Hong Kong(香港中文大学);Shanghai Innovation Institute(上海创新研究院);Alibaba Cloud(阿里巴巴云)