资源分类
》 资源 》论文》OPTION DISCOVERY USING DEEP SKILL CHAINING

OPTION DISCOVERY USING DEEP SKILL CHAINING

2020-01-02 | |  44 |   36 |   0

Abstract

Autonomously discovering temporally extended actions, or skills, is a longstanding goal of hierarchical reinforcement learning. We propose a new algorithm that combines skill chaining with deep neural networks to autonomously discover skills in high-dimensional, continuous domains. The resulting algorithm, deep skill chaining, constructs skills with the property that executing one enables the agent to execute another. We demonstrate that deep skill chaining significantly outperforms both non-hierarchical agents and other state-of-the-art skill discovery techniques in challenging continuous control tasks.1

上一篇：NAS-B ENCH -1S HOT 1:B ENCHMARKING AND DISSECTINGO NE -SHOT NEURAL ARCHITECTURE SEARCH

下一篇：WHY GRADIENT CLIPPING ACCELERATES TRAINING :A THEORETICAL JUSTIFICATION FOR ADAPTIVITY

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...