论文笔记 Retrospective Analysis of the 2019MineRL Competition on Sample Efficient Reinforcement Learning
摘要 论文作者在NeurIPS2019举办了在利用人类先验知识的sample-efficient强化学习上的MineRL挑战赛。强化学习中agent和环境的交互成本较高，若一个算法可以尽量少地与环境交互，即用尽量少的样本数量进行训练，则该算法是sample efficient的。MineRL挑战赛旨在发展使用协同人类示范（human demonstration）的强化学习来减少样本数量的算法。这些
相关文章
- 1. 论文笔记 Reinforcement Learning with Derivative-Free Exploration
- 2. 论文笔记 Benchmarking Model-Based Reinforcement Learning
- 3. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning 论文笔记
- 4. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning论文笔记
- 5. 【论文笔记】Deep Learning on Graphs: A Survey
- 6. Deep Learning on Graphs: A Survey论文笔记
- 7. 论文笔记：《Playing Atari with Deep Reinforcement Learning》
- 8. 论文笔记：Learning how to Active Learn: A Deep Reinforcement Learning Approach
- 9. 论文笔记——NEURAL ARCHITECTURE SEARCH WITH REINFORCEMENT LEARNING
- 10. 论文笔记《Neural Architecture Search With Reinforcement Learning》
- 更多相关文章...
- • CAP理论是什么？ - NoSQL教程
- • XSLT
- • 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。
最新文章
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文笔记 Reinforcement Learning with Derivative-Free Exploration
- 2. 论文笔记 Benchmarking Model-Based Reinforcement Learning
- 3. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning 论文笔记
- 4. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning论文笔记
- 5. 【论文笔记】Deep Learning on Graphs: A Survey
- 6. Deep Learning on Graphs: A Survey论文笔记
- 7. 论文笔记：《Playing Atari with Deep Reinforcement Learning》
- 8. 论文笔记：Learning how to Active Learn: A Deep Reinforcement Learning Approach
- 9. 论文笔记——NEURAL ARCHITECTURE SEARCH WITH REINFORCEMENT LEARNING
- 10. 论文笔记《Neural Architecture Search With Reinforcement Learning》