Abstract
Deep reinforcement learning (DRL) is mainly applied to solve the perception-decision problem, and has become an important research branch in the field of artificial intelligence. Two kinds of DRL algorithms based on value function and policy gradient were summarized, including deep Q network, policy gradient as well as related developed algorithms. In addition, the applications of DRL in video games, navigation, multi-agent cooperation and recommendation field were intensively reviewed. Finally, a prospect for the future research of DRL was made, and some research suggestions were given.
| Translated title of the contribution | An overview on algorithms and applications of deep reinforcement learning |
|---|---|
| Original language | Chinese (Traditional) |
| Pages (from-to) | 314-326 |
| Number of pages | 13 |
| Journal | Chinese Journal of Intelligent Science and Technology |
| Volume | 2 |
| Issue number | 4 |
| DOIs | |
| State | Published - Dec 2020 |
| Externally published | Yes |