Latent Space Policies for Hierarchical Reinforcement Learning
基于潜变量的层级强化学习，主要依赖的工作有：SAC和real NVP 摘要 本文的目标是设计一个层级强化学习算法，按照自底向上的方式逐层构建分层表示。不同与以往HRL强制底层agent使用高层信号，从而限制或削弱其能力，进而强制层次生成，本文提出的框架中的每一层都致力于直接完成任务。 框架内的每一层都被添加了潜变量，可从先验分布中采样得到。最大熵强化学习将这些潜变量和每一层的策略结合起来，并且高层
相关文章
- 1. FeUdal Networks for Hierarchical Reinforcement Learning 阅读笔记
- 2. Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- 3. 《A Hierarchical Framework for Relation Extraction with Reinforcement Learning》论文整理
- 4. Policy in Reinforcement Learning
- 5. Deep Reinforcement Learning with a Natural Language Action Space
- 6. Policy Iterations for Reinforcement Learning Problems in Continuous Time and Space—Fundamental Theor
- 7. Learning Hierarchical Features for Scene Labeling
- 8. [cvpr2017]Learning an Invariant Hilbert Space for Domain Adaptation
- 9. Deep Reinforcement Learning for Dialogue Generation
- 10. Deep Reinforcement Learning for Join Order Enumeration
- 更多相关文章...
- • XSLT
- • Swift for 循环 - Swift 教程
- • 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解
- • Java Agent入门实战（三）-JVM Attach原理与使用
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. FeUdal Networks for Hierarchical Reinforcement Learning 阅读笔记
- 2. Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- 3. 《A Hierarchical Framework for Relation Extraction with Reinforcement Learning》论文整理
- 4. Policy in Reinforcement Learning
- 5. Deep Reinforcement Learning with a Natural Language Action Space
- 6. Policy Iterations for Reinforcement Learning Problems in Continuous Time and Space—Fundamental Theor
- 7. Learning Hierarchical Features for Scene Labeling
- 8. [cvpr2017]Learning an Invariant Hilbert Space for Domain Adaptation
- 9. Deep Reinforcement Learning for Dialogue Generation
- 10. Deep Reinforcement Learning for Join Order Enumeration