The emerging field of \emph{value awareness engineering} claims that software agents and systems should be value-aware, i.e. they must make decisions in accordance with human values. In this context, such agents must be capable of explicitly reasoning as to how far different courses of action are aligned with these values. For this purpose, values are often modelled as preferences over states or actions, which are then aggregated to determine the sequences of actions that are maximally aligned with a certain value. Recently, additional value admissibility constraints at this level have been considered as well.
However, often relaxed versions of these constraints are needed, and this increases considerably the complexity of computing value-aligned policies. To obtain efficient algorithms that make value-aligned decisions considering admissibility relaxation, we propose the use of learning techniques, in particular, we have used constrained reinforcement learning algorithms. In this paper, we present two algorithms, $ε\text{-}ADQL$ for strategies based on local alignment and its extension $ε\text{-}CADQL$ for a sequence of decisions. We have validated their efficiency in a water distribution problem in a drought scenario.
Active Advantage-Aligned Online Reinforcement Learning with Offline Data
Department of Computer Science, University of Chicago(计算机科学系,芝加哥大学);Department of Statistics and Data Science, Yale University(统计与数据科学系,耶鲁大学);Toyota Technological Institute at Chicago(芝加哥丰田技术研究所)
Optimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes
Simon Fraser University(西蒙菲莎大学);University of Pennsylvania(宾夕法尼亚大学);Mila, McGill University(Mila,麦吉尔大学);Google DeepMind(谷歌DeepMind);University of Alberta(阿尔伯塔大学)
CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction
University of North Carolina at Charlotte(北卡罗来纳大学夏洛特分校);North Carolina Battery Complexity, Autonomous Vehicle and Electrification (BATT CAVE) Research Center(北卡罗来纳州电池复杂性、自动驾驶与电气化(BATT CAVE)研究中心)
Enhancing Aerial Combat Tactics through Hierarchical Multi-Agent Reinforcement Learning
Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA), USI-SUPSI(瑞士智能系统研究所(IDSIA)及USI-SUPSI);Armasuisse Science + Technology(Armasuisse科学与技术)
Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning
Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur(计算机科学与工程系,印度理工学院Kharagpur分校);Department of Mechanical Engineering, Indian Institute of Technology Kharagpur(机械工程系,印度理工学院Kharagpur分校)
Mind and Motion Aligned: A Joint Evaluation IsaacSim Benchmark for Task Planning and Low-Level Policies in Mobile Manipulation
AIRI;Moscow Institute of Physics and Technology (MIPT)(莫斯科物理技术学院);Lomonosov Moscow State University(罗蒙诺索夫莫斯科国立大学);Sberbank, Robotics Center(Sberbank机器人中心);Skoltech
本文提出 Kitchen-R 基准,在 Isaac Sim 数字孪生厨房环境中统一评估任务规划与底层控制,并提供视觉语言模型规划、扩散策略控制及轨迹采集系统,支持独立与集成评估,弥补具身 AI 中语言引导机器人整体评测的空白。
Atomic Action Slicing: Planner-Aligned Options for Generalist VLA Agents
Sofia University 'St. Kliment Ohridski(索菲亚大学 '圣克莱门特·欧里基斯基');Technical University of Sofia(索菲亚技术大学);EEMCS, University of Twente(EEMCS,特文特大学);GATE Institute, Sofia University 'St. Kliment Ohridski(GATE研究所,索菲亚大学 '圣克莱门特·欧里基斯基')
Constraint-Anchored Attribution: Feasibility-Certified Counterfactuals and Bonferroni-PAC Sufficient Subsets for Neural CO Policies
Univ. Artois, UR 3926, Laboratoire de G\'enie Informatique et d'Automatique de l'Artois (LGI2A) B\'ethune F-62400 France;Univ. Artois, UR 3926, Laboratoire de G\'enie Informatique et d'Automatique de l'Artois (LGI2A)
SORA-ATMAS: Adaptive Trust Management and Multi-LLM Aligned Governance for Future Smart Cities
organization= Department of Computer Science, National University of Computer \& Emerging Sciences , addressline= St-4 Sector 17-D On National Highway , city= Karachi , postcode= 75160 , state= , country= Pakistan;organization= Balochistan University of Information Technology, Engineering;organization= Department of Computer Science, Birmingham City University , addressline= STEAMhouse, Belmont Row , city= Birmingham , postcode= B4 7RQ , country= United Kingdom
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
Institute for Artificial Intelligence, Peking University(人工智能研究院,北京大学);PKU-PsiBot Joint Lab(北京大学PsiBot联合实验室);State Key Laboratory of General Artificial Intelligence, Peking University(通用人工智能国家重点实验室,北京大学);Zhongguancun Academy(中关村学院)