A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. In this class of problems, we show a simple example in which the desired optimal policy cannot be induced by any weighted linear combination of rewards. Hence, there exist constrained reinforcement learning problems for which neither regularized nor classical primal-dual methods yield optimal policies. This work addresses this shortcoming by augmenting the state with Lagrange multipliers and reinterpreting primal-dual methods as the portion of the dynamics that drives the multipliers evolution. This approach provides a systematic state augmentation procedure that is guaranteed to solve reinforcement learning problems with constraints. Thus, as we illustrate by an example, while previous methods can fail at finding optimal policies, running the dual dynamics while executing the augmented policy yields an algorithm that provably samples actions from the optimal policy.
Harnessing VLM in Embodied RL: From Reward Regressor to Success Detector via Exploration-Augmented Key-Observation Gating
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所 多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of the Chinese Academy of Sciences（中国科学院大学 人工智能学院）；AGIBOT
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning
School of Computer Science, Peking University（北京大学计算机科学学院）；College of AI, Tsinghua University（清华大学人工智能学院）；Imperial College London（伦敦帝国理工学院）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
Spatiotemporal Attention-Augmented Inverse Reinforcement Learning for Multi-Agent Task Allocation
College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学智能自主系统上海研究院）；Graz University of Technology（格拉茨技术大学）；Virtual Vehicle Research GmbH（虚拟车辆研究公司）
ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Chinese Academy of Sciences（中国科学院）；Tsinghua University（清华大学）
Clemson University（克莱姆森大学）；Université de Montréal（蒙特利尔大学）；Accenture (United States)（埃森哲（美国））；Arizona State University（亚利桑那州立大学）；Northeastern University（东北大学）
Decision Making for Autonomous Driving via Augmented Adversarial Inverse Reinforcement Learning
University of California, Berkeley（加州大学伯克利分校）；Zenseact（森赛克特）；Chalmers University of Technology（查尔姆斯理工大学）；Peking University（北京大学）；Google Research（谷歌研究院）
Capsule Network Performance with Autonomous Navigation
Purdue University（普渡大学）
胶囊网络（CapsNets）已经被提出作为卷积神经网络（CNN）的替代方案。本文展示了CapsNets如何比CNN更有能力进行自主智能体对现实场景的探索。在现实世界的导航，奖励外部代理可能是罕见的。反过来，强化学习算法可能难以形成有意义的策略函数。本文的方法Capsules Exploration Module（Caps-EM）将CapsNets架构与Advantage Actor Critic算法配对。用于导航稀疏环境的其他方法需要内在奖励生成器，诸如内在Currency模块（ICM）和增强Currency模块（ACM）。Caps-EM使用更紧凑的架构，无需内在奖励。使用ViZDoom进行测试，Caps-EM使用的可训练网络参数分别比ICM和深度增强Currency模块（D-ACM）少44%和83%，平均时间分别比ICM和D-ACM提高1141%和437%，以在“My Way Home”场景中收敛到策略功能。
R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China（上海可信计算实验室，华东师范大学，上海，中国）；Huazhong University of Science and Technology（华中科技大学）；Nanyang Technological University（南洋理工大学）
Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents
AI Research and Innovation Nexus for Africa (AIRINA Labs)（非洲AI研究与创新中心（AIRINA实验室））；Sefako Makgatho Health Sciences University (SMU)（塞法科·马加托健康科学大学）；African Center for Advanced Studies (ACAS)（非洲高级研究中心）；African Institute for Mathematical Sciences（非洲数学科学学院）
Pompeu Fabra University（庞培法布拉大学）；ICREA（加泰罗尼亚高级研究学院）；Barcelona Graduate School of Economics（巴塞罗那经济学研究生院）；Imperial College London（伦敦帝国理工学院）；Cisco Systems, Inc.（思科系统公司）
Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
Harbin Institute of Technology SCIR Lab（哈尔滨工业大学SCIR实验室）；Huawei Technologies Co., Ltd（华为技术有限公司）；Shanghai Jiao Tong University（上海交通大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Adobe Inc.（Adobe公司）；Department of Computer Science, University of California, Santa Barbara（加州大学圣芭芭拉分校计算机科学系）
Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；South China University of Technology（华南理工大学）；Nankai University（南开大学）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
