階層的ニューラルオプションと抽象世界モデルの同時学習
Joint Learning of Hierarchical Neural Options and Abstract World Model
抽象世界モデルと階層的ニューラルオプションを同時に学習するAgentOWLを提案し、少ないデータでより多くのスキルを獲得できることを示した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Wasu Top Piriyakulkij, Wolfgang Lehrach, Kevin Ellis, Kevin Murphy
分類: cs.LG, cs.AI
原文アブストラクト
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.
