Abstract | ||
---|---|---|
•Deep Reinforcement Learning is efficient in solving some combinatorial optimization problems.•Credit assignment can be used to reduce the high sample complexity of Deep Reinforcement Learning algorithms.•Model-free and model-based reinforcement learning algorithms can be connected to solve large-scale problems.•Assign credits for hundreds of thousands of state-action pairs in a systemic manner will accelerate the training process. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.patcog.2021.108466 | Pattern Recognition |
Keywords | DocType | Volume |
Combinatorial optimization,Reinforcement learning,Credit assignment | Journal | 124 |
ISSN | Citations | PageRank |
0031-3203 | 0 | 0.34 |
References | Authors | |
9 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dong Yan | 1 | 17 | 6.40 |
Jiayi Weng | 2 | 0 | 0.68 |
Shiyu Huang | 3 | 0 | 0.34 |
Chongxuan Li | 4 | 125 | 12.29 |
Yichi Zhou | 5 | 0 | 3.72 |
Hang Su | 6 | 0 | 0.34 |
Jun Zhu | 7 | 1926 | 154.82 |