Cooperative Navigation (3v0) on Multi-agent particle environment (MPE) (test)
155.88Mean Episode Extrinsic RewardELIGN_self
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ELIGN_selfPartial observability=true, Decentralized training=true, Agt# v Adv#=3v02022.10 | 155.88 | 5.11 | |
| ELIGN_teamPartial observability=true, Decentralized training=true, Agt# v Adv#=3v02022.10 | 141.04 | 8.04 | |
| SPARSEPartial observability=true, Decentralized training=true, Agt# v Adv#=3v02022.10 | 139.07 | 13.63 | |
| CURIO_selfPartial observability=true, Decentralized training=true, Agt# v Adv#=3v02022.10 | 133.93 | 7.66 | |
| CURIO_teamPartial observability=true, Decentralized training=true, Agt# v Adv#=3v02022.10 | 125.42 | 11.95 | |
| HAND-CRAFTEDPartial observability=true, Decentralized training=true, Agt# v Adv#=3v02022.10 | 75.56 | 18.9 |