Q-learning with Continuous Action Value in Multi-agent Cooperation
碩士 === 國立中正大學 === 電機工程所 === 94 === In this thesis, we propose a Q-learning with continuous action space and extend this algorithm to a multi-agent system. We implement this algorithm in a task that there are two robots taking action independently and both are connected with a straight bar. They must...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Online Access: | http://ndltd.ncl.edu.tw/handle/36513682200450671073 |