Mission schedule of agile satellites based on Proximal Policy Optimization Algorithm

在自主赛车中学习调整纯追求：联合前瞻和转向增益控制的PPO方法

Learning to Tune Pure Pursuit in Autonomous Racing: Joint Lookahead and Steering-Gain Control with PPO

本文提出基于PPO的强化学习方法，联合优化纯追求算法的前瞻距离和转向增益，提升自主赛车的路径跟踪性能。

PPO-STGNN：一种用于云边端计算中DAG任务调度的结合时空图神经网络的近端策略优化方法

PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing

该研究针对云边端计算中异构节点下DAG任务调度的NP难问题，提出PPO-STGNN算法，结合STGNN提取时空特征、PPO优化策略，经多教师行为克隆预训练后，在负载均衡与完成时间上表现更优，适配动态异构调度场景。

Learning to schedule job-shop problems: Representation and policy learning using graph neural network and reinforcement learning

We propose a framework to learn to schedule a job-shop problem (JSSP) using a graph neural network (GNN) and reinforcement learning (RL). We formulate the scheduling process of JSSP as a sequential decision-making problem with graph representation of the state to consider the structure of JSSP. In solving the formulated problem, the proposed framework employs a GNN to learn that node features that embed the spatial structure of the JSSP represented as a graph (representation learning) and derive the optimum scheduling policy that maps the embedded node features to the best scheduling action (p…

自滚动近端梯度下降：一种AutoML方法用于可解释的波形优化

Auto-Unrolled Proximal Gradient Descent: An AutoML Approach to Interpretable Waveform Optimization

本文提出通过AutoML与模型驱动的深度展开结合，优化无线波束成形和波形。通过将迭代近端梯度下降算法转化为深度神经网络，实现参数学习而非预设，结合混合层提升架构，利用AutoGluon进行超参数优化，实现仅用五层卷积即可达到传统200次迭代的谱效率，同时减少训练数据和推理成本。

面向时间敏感型应用的在线流量调度的多智能体强化学习

Multi-Agent Reinforcement Learning for Online Traffic Scheduling in Time-Sensitive Application

针对动态XR驱动的MEC场景中TSN调度的挑战，本文提出基于HAPPO算法的MARL框架，将各TSN队列建模为自主智能体，可降低平均帧等待时间最多26.8%、最坏情况延迟约16.8%。

面向负荷、光伏发电与能源价格不确定性的社区电池调度深度强化学习方法

Deep Reinforcement Learning for Community Battery Scheduling under Uncertainties of Load, PV Generation, and Energy Prices

本文提出以SAC为核心并结合噪声网络的深度强化学习策略，在PV、负荷和价格不确定下实现社区电池的多重调度目标，实验证明其优于PPO、DDPG及优化基准。

基于图学习的考虑运行约束、需求变化与不确定性的城市空中交通机队调度

Graph Learning-based Fleet Scheduling for Urban Air Mobility under Operational Constraints, Varying Demand & Uncertainties

本文提出一种图强化学习方法用于城市空中交通机队的在线调度，通过图胶囊卷积网络、Transformer层和多头注意力解码器构建策略架构，在多变需求与不确定性约束下，相比基线和遗传算法实现更高利润且执行速度大幅提升。

面向NOMA-URLLC网络上行链路调度的深度强化学习方法

Deep Reinforcement Learning for Uplink Scheduling in NOMA-URLLC Networks

针对NOMA上行URLLC调度的组合动作空间与部分可观测挑战，提出融合POMDP转化、改进PPO与贝叶斯先验的NOMA-PPO算法，在3GPP场景下性能优于传统协议与DRL基准且鲁棒性强。

TT-DAC-PS：用于最优交易执行的双目标确定性演员-评论家与策略平滑

TT-DAC-PS: Twin-Target Deterministic Actor-Critic with Policy Smoothing for Optimal Trade Execution

提出TT-DAC-PS算法，结合双指数移动平均评论家目标、悲观最小备份、TD3风格策略平滑噪声、延迟演员更新和保守Q正则化，以抑制过高估计，并在限价订单簿数据上优于经典和强化学习基线。

ACPO：面向复杂推理中视觉语言模型对齐的自适应课程策略优化

ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning

针对视觉语言模型强化学习对齐中现有策略优化的缺陷，提出含动态课程与优势感知自适应裁剪的ACPO框架，在多模态推理基准上实现更优性能、更快收敛与更高稳定性。