Heterogeneous Navigation (4v0) on Multi-agent particle environment (MPE) (test)
311.67Mean Episode Extrinsic RewardELIGN_team
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ELIGN_teamPartial observability=true, Decentralized training=true, Agt# v Adv#=4v02022.10 | 311.67 | 10.88 | |
| ELIGN_selfPartial observability=true, Decentralized training=true, Agt# v Adv#=4v02022.10 | 292.34 | 9.24 | |
| CURIO_selfPartial observability=true, Decentralized training=true, Agt# v Adv#=4v02022.10 | 286.22 | 9.97 | |
| SPARSEPartial observability=true, Decentralized training=true, Agt# v Adv#=4v02022.10 | 284.42 | 12.83 | |
| CURIO_teamPartial observability=true, Decentralized training=true, Agt# v Adv#=4v02022.10 | 262.28 | 22.59 | |
| HAND-CRAFTEDPartial observability=true, Decentralized training=true, Agt# v Adv#=4v02022.10 | 228.48 | 18.88 |