Physical Deception (2v1) on Multi-agent particle environment (MPE) (test)
101.72Mean Extrinsic RewardELIGN_team
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ELIGN_teamPartial observability=true, Decentralized training=true, Agt# v Adv#=2v12022.10 | 101.72 | 6.31 | |
| HAND-CRAFTEDPartial observability=true, Decentralized training=true, Agt# v Adv#=2v12022.10 | 94.25 | 14.75 | |
| SPARSEPartial observability=true, Decentralized training=true, Agt# v Adv#=2v12022.10 | 93.6 | 8.61 | |
| ELIGN_advPartial observability=true, Decentralized training=true, Agt# v Adv#=2v12022.10 | 92.2 | 4.23 | |
| CURIO_teamPartial observability=true, Decentralized training=true, Agt# v Adv#=2v12022.10 | 85.31 | 11.93 | |
| ELIGN_selfPartial observability=true, Decentralized training=true, Agt# v Adv#=2v12022.10 | 69.91 | 4.51 | |
| CURIO_selfPartial observability=true, Decentralized training=true, Agt# v Adv#=2v12022.10 | 68.8 | 7.93 |