Taking inspiration from developmental learning, we present a novel reinforcement learning architecture which hierarchically learns and represents self-generated skills in an end-to-end way. With this architecture, an agent focuses only on task-rewarded skills while keeping the learning process of skills bottom-up. This bottom-up approach allows to learn skills that 1- are transferable across tasks, 2- improves exploration when rewards are sparse. To do so, we combine a previously defined mutual information objective with a novel curriculum learning algorithm, creating an unlimited and explorable tree of skills. We test our agent on simple gridworld environments to understand and visualize how the agent distinguishes between its skills. Then we show that our approach can scale on more difficult MuJoCo environments in which our agent is able to build a representation of skills which improve over a baseline both transfer learning and exploration when rewards are sparse.
Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills
The Hong Kong University of Science（香港科技大学）；University of Chinese Academy of Sciences Beijing, China（中国科学院大学）；Institute of Software, Chinese Academy of Sciences Beijing, China（中国科学院软件研究所）；Zhejiang University Hangzhou, China（浙江大学）
Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
Key Laboratory of Interdisciplinary Research of Computation and Economics（交叉计算与经济学交叉研究实验室）；Shanghai University of Finance and Economics（上海财经大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, Chinese Academy of Sciences（中国科学院人工智能研究所）；University of Bristol（布里斯托大学）；Peking University（北京大学）；University College London（伦敦大学学院）
Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
C2DL, Institute of Automation, Chinese Academy of Sciences（C2DL，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）；Tencent AI Lab（腾讯AI实验室）；Tsinghua University（清华大学）
ASPiRe:Adaptive Skill Priors for Reinforcement Learning
Columbia University（哥伦比亚大学）；J.P. Morgan AI Research（摩根大通人工智能研究院）；Carnegie Mellon University（卡内基梅隆大学）
我们引入了ASPiRe（Adaptive Skill Prior for RL），这是一种利用先前经验来加速强化学习的新方法。与现有的从大型和多样化的数据集中学习单个技能先验的方法不同，我们的框架学习不同区分技能先验的库（即，行为先验），并学习如何将它们组合起来解决新任务。该公式允许算法获取一组更可重用的下游任务的专业技能先验;然而，它也带来了如何有效地组合这些非结构化的技能先验集合以形成新任务的新先验的额外挑战。具体来说，它不仅要求智能体确定要使用哪些技能先验，而且还要求智能体确定如何将它们组合（顺序或同时）以形成新的先验。为了实现这一目标，ASPiRe包括自适应权重模块（AWM），该模块学习推断不同技能先验之间的自适应权重分配，并使用它们通过加权Kullback-Leibler分歧来指导下游任务的策略学习。我们的实验表明，ASPiRe可以显着加快学习新的下游任务在存在多个先验，并显示出竞争基线的改善。
SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China（认知与决策智能复杂系统重点实验室，自动化研究所，中国科学院，北京，中国）；School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（中国科学院大学人工智能学院，北京，中国）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室，上海，中国）；Beijing Academy of Artificial Intelligence, Beijing, China（北京人工智能研究院，北京，中国）
From Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation
National University of Defense Technology（国防科技大学）；Nanyang Technological University（南洋理工大学）；The Hong Kong Polytechnic University（香港理工大学）；Southeast University（东南大学）
What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.md Files
The Graduate Center, City University of New York（纽约城市大学研究生中心）；The Ohio State University（俄亥俄州立大学）；Hunter College, City University of New York（纽约城市大学亨特学院）
VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience
Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing University of Post and Telecommunications（北京邮电大学）
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning
Hangzhou Dianzi University（杭州电子科技大学）；Central South University（中南大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Sun Yat-sen University（中山大学）；Ramus；Hong Kong University of Science and Technology (GuangZhou)（香港科技大学（广州））
Beyond Prompt or Skill? Attribution-Guided Optimization of Modular LLM Programs
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen)（深圳未来智能网络研究院（深圳FNii））；Sun Yat-sen University（中山大学）
