AUSO: Action-Level Unified Skill Optimization from Internalization to Utilization
[Sztuczna inteligencja] Autorzy: Huizu Lin, Chengkai Huang, Tianqi Gao i 5 więcej
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 of training, AUSO jointly learns from teacher guidance and environmental outcomes, enabling the po…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja