Reinforcement Learning with Budget-Constrained Nonparametric Function Approximation for Opportunistic Spectrum Access

Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams

In many real-world learning scenarios, features are only acquirable at a cost constrained under a budget. In this paper, we propose a novel approach for cost-sensitive feature acquisition at the prediction-time. The suggested method acquires features incrementally based on a context-aware feature-value function. We formulate the problem in the reinforcement learning paradigm, and introduce a reward function based on the utility of each feature. Specifically, MC dropout sampling is used to measure expected variations of the model uncertainty which is used as a feature-value function. Furthermor…

Exploring Partially Observed Networks with Nonparametric Bandits

Real-world networks such as social and communication networks are too large to be observed entirely. Such networks are often partially observed such that network size, network topology, and nodes of the original network are unknown. In this paper we formalize the Adaptive Graph Exploring problem. We assume that we are given an incomplete snapshot of a large network and additional nodes can be discovered by querying nodes in the currently observed network. The goal of this problem is to maximize the number of observed nodes within a given query budget. Querying which set of nodes maximizes the …

BiPACE：基于双模拟引导与动作反事实估计的LLM智能体策略优化

BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents

针对分组强化学习中状态-动作信用分配不匹配问题，提出BiPACE优势估计器，通过双模拟引导的状态聚类和动作反事实基线，在无需批评网络或额外采样的前提下提升LLM智能体训练效果。

增强认知无线电网络频谱感知的主动可重构智能表面

Active Reconfigurable Intelligent Surface Enhanced Spectrum Sensing for Cognitive Radio Networks

针对认知无线电中弱信号下感知时间长的问题，提出主动 RIS 辅助频谱感知系统，通过 WMMSE 算法优化反射系数矩阵以提升检测概率，并揭示了主被动 RIS 在不同干扰强度下的性能优势。