Generalized Advantage Estimation

引用本概念的论文(2)

• CompactionRL：基于上下文压缩的强化学习用于长视野智能体 CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents arXiv 2607.05378
• 面向智能体强化学习的单次采样异步优化 Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning arXiv 2607.07508

共现相关概念

在引用本概念的论文中,与下列概念同时出现的次数(降序)。