Research Article
Optimizing the Junction-Tree-Based Reinforcement Learning Algorithm for Network-Wide Signal Coordination
Table 1
The given Q-value matrix of the virtual road network.
| | Phase combination | Intersection and phase | | Intersection and phase | | Intersection and phase | | Intersection and phase | | | 1 | 2 | 1 | 3 | 3 | 4 | 2 | 4 |
| | Combination 1 | A | A | 4 | A | A | 8 | A | A | 7 | A | A | 8 | | Combination 2 | A | B | 5 | A | B | 7 | A | B | 6 | A | B | 9 | | Combination 3 | B | A | 3 | B | A | 5 | B | A | 4 | B | A | 5 | | Combination 4 | B | B | 7 | B | B | 9 | B | B | 6 | B | B | 7 |
|
|
