提出新方法，让智能体用更少数据学会组合技能。
Joint Learning of Hierarchical Neural Options and Abstract World Model
- 联合学习抽象世界模型与分层神经选项
- 在对象中心的Atari游戏上用更少数据学更多技能
- 适合研究高效强化学习与技能组合的学者
构建能通过组合已有技能完成新任务的智能体是人工智能长期目标。为此，我们研究如何高效获取一系列技能，形式化为分层神经选项。现有无模型分层强化学习方法需大量数据。本文提出新方法AgentOWL（Option and World model Learning Agent），以样本高效方式联合学习抽象世界模型（跨状态与时间抽象）和一组分层神经选项。在部分对象中心的Atari游戏上，该方法比基线方法用更少数据学习更多技能，且具备基线不具备的学习与泛化能力。
原文摘要 · Abstract (English)
Building agents that can perform new skills by composing existing skills is a long-standing goal of AI agent research. Towards this end, we investigate how to efficiently acquire a sequence of skills, formalized as hierarchical neural options. However, existing model-free hierarchical reinforcement algorithms need a lot of data. We propose a novel method, which we call AgentOWL (Option and World model Learning Agent), that jointly learns -- in a sample efficient way -- an abstract world model (abstracting across both states and time) and a set of hierarchical neural options. We show, on a subset of Object-Centric Atari games, that our method can learn more skills using less data than baseline methods and possesses learning and generalization capabilities that the baselines do not have.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。