Deep Reinforcement Learning for High Precision Assembly Tasks
文献目录 本篇论文的目的是控制机械臂在组件装配精度高于机器人控制精度的情况下实现轴孔的装配。本文使用双层LSTM网络结构来作为状态-行为价值函数Q的近似，输入为机械臂的力-力矩传感器反馈信号以及机械臂末端的近似位置，输出为机械臂末端三个轴上施加的力与两个方向上姿态的旋转角度。从演示视频来看效果还是很不错的。 该论文实验中有一个前置条件：假设轴已经被抓且与孔板相接触。那么这篇论文其实就是分两步走：一
相关文章
- 1. PR17.10.2:Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
- 2. Deep Reinforcement Learning for Dialogue Generation
- 3. Deep Reinforcement Learning for Join Order Enumeration
- 4. Deep Reinforcement Learning for List-wise Recommendations
- 5. Deep Reinforcement Learning
- 6. Reinforcement learning and Deep learning
- 7. Building a ROS simulation platform for Deep Reinforcement Learning research ...
- 8. Relational Deep Reinforcement Learning
- 9. (转) Deep Reinforcement Learning: Pong from Pixels
- 10. Playing Atari with Deep Reinforcement Learning
- 更多相关文章...
- • Swift for 循环 - Swift 教程
- • Scala for循环 - Scala教程
- • Java Agent入门实战（一）-Instrumentation介绍与使用
- • Flink 数据传输及反压详解
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. PR17.10.2:Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
- 2. Deep Reinforcement Learning for Dialogue Generation
- 3. Deep Reinforcement Learning for Join Order Enumeration
- 4. Deep Reinforcement Learning for List-wise Recommendations
- 5. Deep Reinforcement Learning
- 6. Reinforcement learning and Deep learning
- 7. Building a ROS simulation platform for Deep Reinforcement Learning research ...
- 8. Relational Deep Reinforcement Learning
- 9. (转) Deep Reinforcement Learning: Pong from Pixels
- 10. Playing Atari with Deep Reinforcement Learning