A Hybrid Planning in Concurrent Dyna-Q Learning for Multi-agent Systems
碩士 === 國立中正大學 === 光機電整合工程研究所 === 100 === Traditional reinforcement learning algorithm, such as Q-learning, is based on one agent and one step learning without a model. In recent years, many have proposed the concepts of multi-agents and using a model for retraining to increase learning efficiency, s...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2012
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/67686939437674667921 |