Abstract | ||
---|---|---|
How to improve the learning efficiency and optimize the encapsulation of subtasks is a key problem that hierarchical reinforcement learning needs to solve. This paper proposes a modular hierarchical reinforcement learning al-gorithm, named MHRL, in which the modularized hierarchical subtasks are trained by their independent reward systems. During learning, the MHRL pro-duces an optimization strategy for different modular layers, which makes inde-pendent modules be able to concurrently execute. In addition, this paper pre-sents some experimental results for solving application problems with nested learning processes. The results show that the MHRL can increase learning reus-ability and improve learning efficiency dramatically. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-31576-3_48 | ICIC (2) |
Keywords | Field | DocType |
key problem,hierarchical reinforcement,different modular layer,nested learning process,inde-pendent module,modularized hierarchical subtasks,independent reward system,modular hierarchical reinforcement,application problem | Instance-based learning,Active learning (machine learning),Computer science,Artificial intelligence,Modular design,Reinforcement learning algorithm,Reward system,Machine learning,Proactive learning,Learning classifier system,Reinforcement learning | Conference |
Volume | ISSN | Citations |
7390 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhibin Liu | 1 | 0 | 0.34 |
Xiaoqin Zeng | 2 | 407 | 32.97 |
HuiYi Liu | 3 | 2 | 1.75 |