层级神经选项与抽象世界模型的联合学习
Joint Learning of Hierarchical Neural Options and Abstract World Model
- Cornell University（康奈尔大学）
- Google Deepmind（谷歌DeepMind）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出AgentOWL方法，通过高效样本学习抽象世界模型和层级神经选项，使智能体在Object-Centric Ataris游戏中以更少数据学习更多技能。
AI中文摘要：
构建能够通过组合现有技能学习新技能的智能体是AI智能体研究的长期目标。为此，我们探讨如何高效地获取一系列技能，将其形式化为层次神经选项。然而，现有的无模型层次强化学习算法需要大量数据。我们提出了一种新方法，称为AgentOWL（选项和世界模型学习智能体），通过高效采样方式联合学习抽象世界模型（跨状态和时间抽象）和一组层次神经选项。我们在Object-Centric Atari游戏的子集上展示了我们的方法在更少数据下学习更多技能的能力，并且具备基线方法所没有的学习和泛化能力。
英文摘要：
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.
