图 书 馆
隐私保护的强化学习Privacy-Preserving Reinforcement Learning |
|
| 课程网址: | http://videolectures.net/icml08_sakuma_ppr/ |
| 主讲教师: | Jun Sakuma |
| 开课单位: | 东京工业大学 |
| 开课时间: | 2008-08-04 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Distributed reinforcement learning (DRL) has been studied as an approach to learn control policies thorough interactions between distributed agents and environments. The main emphasis of DRL has been put on the way to learn sub-optimal policies with the least or limited sharing of agents' perceptions. In this study, we introduce a new concept, privacy-preservation, into DRL. In our setting, agents' perceptions, such as states, rewards, and actions, are not only distributed but also are desired to be kept private. This can occur when agents' perceptions include private or confidential information. Conventional DRL algorithms could be applied to such problems, but do not theoretically guarantee privacy preservation. We design solutions that achieve optimal policies in standard reinforcement leering settings without requiring the agents to share their private information by means of well-known cryptographic primitive, secure function evaluation. |
| 关 键 词: | 分布式强化学习; 隐私保护; 政策标准 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-09-27：yumf |
| 阅读次数: | 171 |