Research Article
Coordinated Learning by Model Difference Identification in Multiagent Systems with Sparse Interactions
Table 1
Results of final learned policy by the tested approaches in the different 2-agent games.
| Env | Alg | # state | # actions | # coll | # step | # reward |
| TTG | CQ | | 4 | | | | MTGA | | 4 | | | | DDL | | 4 | | | | DDL-NI | | 4 | | | |
| TR | CQ | | 4 | | | | MTGA | | 4 | | | | DDL | | 4 | | | | DDL-NI | | 4 | | | |
| HG | CQ | | 4 | | | | MTGA | | 4 | | | | DDL | | 4 | | | | DDL-NI | | 4 | | | |
| ISR | CQ | | 4 | | | | MTGA | | 4 | | | | DDL | | 4 | | | | DDL-NI | | 4 | | | |
| CIT | CQ | | 4 | | | | MTGA | | 4 | | | | DDL | | 4 | | | | DDL-NI | | 4 | | | |
| CMU | CQ | | 4 | | | | MTGA | | 4 | | | | DDL | | 4 | | | | DDL-NI | | 4 | | | |
|
|