论文笔记 Reinforcement Learning with Derivative-Free Exploration
摘要 高效的探索是sample-efficient强化学习的关键。目前最普遍常用的方法（如-greedy）仍是低效率的，而无梯度优化（derivative-free optimization）发明了高效的方法来更好地全局搜索。本文介绍一种无梯度探索（DFE）作为一种早期强化学习的常用高效探索方法。DFE克服了基于纯无梯度优化的强化学习方法的优化低效和可扩展性差的缺点。本文实验通过在确定离线策略方法
相关文章
- 1. 论文笔记——NEURAL ARCHITECTURE SEARCH WITH REINFORCEMENT LEARNING
- 2. 论文笔记《Neural Architecture Search With Reinforcement Learning》
- 3. 【论文笔记】NEURAL COMBINATORIAL OPTIMIZATION WITH REINFORCEMENT LEARNING
- 4. 论文笔记：《Playing Atari with Deep Reinforcement Learning》
- 5. Hierarchical Object Detection with Deep Reinforcement Learning论文笔记
- 6. 论文笔记 Benchmarking Model-Based Reinforcement Learning
- 7. 论文阅读笔记《Ranking Sentences for Extractive Summarization with Reinforcement Learning》
- 8. Mastering Complex Control in MOBA Games with Deep Reinforcement Learning（论文笔记）
- 9. 论文笔记系列-Neural Architecture Search With Reinforcement Learning
- 10. Generating Test Input with Deep Reinforcement Learning 论文笔记
- 更多相关文章...
- • ASP.NET Razor - 标记 - ASP.NET 教程
- • CAP理论是什么？ - NoSQL教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • Scala 中文乱码解决
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. 论文笔记——NEURAL ARCHITECTURE SEARCH WITH REINFORCEMENT LEARNING
- 2. 论文笔记《Neural Architecture Search With Reinforcement Learning》
- 3. 【论文笔记】NEURAL COMBINATORIAL OPTIMIZATION WITH REINFORCEMENT LEARNING
- 4. 论文笔记：《Playing Atari with Deep Reinforcement Learning》
- 5. Hierarchical Object Detection with Deep Reinforcement Learning论文笔记
- 6. 论文笔记 Benchmarking Model-Based Reinforcement Learning
- 7. 论文阅读笔记《Ranking Sentences for Extractive Summarization with Reinforcement Learning》
- 8. Mastering Complex Control in MOBA Games with Deep Reinforcement Learning（论文笔记）
- 9. 论文笔记系列-Neural Architecture Search With Reinforcement Learning
- 10. Generating Test Input with Deep Reinforcement Learning 论文笔记