AUSO: Action-Level Unified Skill Optimization from Internalization to Utilization· AUSO: 动作级统一技能优化
Skills play different roles as an agent's policy evolves: they should first provide learnable knowledge, then support capability formation, and finally be invoked only when they improve individual decisions. Existing methods rarely model this lifecycle. They either keep skills outside the model, fully internalize them, or select among internalization and utilization objectives through noisy task-level success rates. Such designs fragment training and assign uniform importance to actions within the same trajectory, even though skill guidance may help some decisions while distracting others. To solve these problems, we introduce AUSO (Action-level Unified Skill Optimization), which unifies skill learning and skill use through a progressive, action-aware optimization process. At the beginning
统一动作级技能优化，提高智能体学习和使用技能的效果。
- 核心方法
- 提出AUSO框架，通过渐进式、动作感知的优化过程将技能学习和使用统一起来。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 现有的技能学习方法未能有效建模技能从学习到使用的整个生命周期，导致训练过程分裂且动作重要性分配不均。
- 关键实验
- 在多种环境下的实验验证了AUSO比现有方法在技能学习和使用上的优势。
- 主要贡献
- AUSO能更有效地整合技能学习和使用，改善智能体决策质量。
- 意义与局限
- 该方法有助于优化智能体的训练过程，提高技能在实际任务中的应用效率。但可能在复杂多变的环境下面临挑战。