Efficient reinforcement learning for robots using informative simulated priors
Autonomous learning through interaction with the physical world is a promising approach to designing controllers and decision-making policies for robots. Unfortunately, learning on robots is often difficult due to the large number of samples needed for many learning algorithms. Simulators are one wa...
| Main Authors: | , |
|---|---|
| 其他作者: | |
| 格式: | 文件 |
| 语言: | en_US |
| 出版: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
| 在线阅读: | http://hdl.handle.net/1721.1/109303 https://orcid.org/0000-0003-0776-7901 https://orcid.org/0000-0001-8576-1930 |