Name
Abstract | ||
|---|---|---|
As a widely used machine learning method, reinforcement learning (RL) is a very effective way to solve decision and control problems where learning skills are needed. In this paper, a knowledge transfer method between multi-granularity models is proposed for RL to speed up the learning process and adapt to the dynamic environments. The learning process runs on naturally organized multi-granularity models, e.g., the coarse grained model and the fine-grained model. This multi-granularity model constitutes a knowledge transfer architecture that bridges the reinforcement learning between different granularity levels. The proposed multi-granularity reinforcement learning (MGRL) approach and related algorithms can scale up very well and speed up learning with other granularity learning process. Several groups of simulation experiments are carried out using a puzzle problem in a gridworld environment. The results demonstrate the effectiveness and efficiency of the proposed approach. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/SMC.2018.00490 | 2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) |
Keywords | Field | DocType |
Knowledge transfer, Multi-granularity, Reinforcement learning | Architecture,SCALE-UP,Computer science,Knowledge transfer,Artificial intelligence,Granularity,Machine learning,Reinforcement learning,Speedup | Conference |
ISSN | Citations | PageRank |
1062-922X | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bo Xin | 1 | 41 | 5.13 |
| Kaiqiang Tang | 2 | 0 | 1.35 |
| Lan Wang | 3 | 1474 | 108.67 |
| Chunlin Chen | 4 | 105 | 9.93 |