Abstract | ||
---|---|---|
Deep reinforcement learning methods are developed to deal with challenging locomotion control problems in a robotics domain and can achieve significant performance improvement over conventional control methods. One of their appealing advantages is model-free. In other words, agents learn a control policy completely from scratches with raw high-dimensional sensory observations. However, they often ... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/MCI.2019.2919364 | IEEE Computational Intelligence Magazine |
Keywords | Field | DocType |
Deep learning,Reinforcement learning,Robot sensing systems,Neural networks | Asynchronous communication,Computer science,Parametric statistics,Robot locomotion,Artificial intelligence,Artificial neural network,Computer engineering,Variance reduction,Robotics,Performance improvement,Reinforcement learning | Journal |
Volume | Issue | ISSN |
14 | 3 | 1556-603X |
Citations | PageRank | References |
3 | 0.39 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhengcai Cao | 1 | 7 | 0.76 |
Qing Xiao | 2 | 10 | 1.85 |
MengChu Zhou | 3 | 8989 | 534.94 |