Predator-Prey (2v2) on Multi-agent particle environment (MPE) (test)
-0.77Mean Episode Extrinsic RewardHAND-CRAFTED
Evaluation results
| Method | Links | ||
|---|---|---|---|
| HAND-CRAFTEDPartial observability=true, Decentralized training=true, Agt# v Adv#=2v22022.10 | -0.77 | 0.17 | |
| ELIGN_advPartial observability=true, Decentralized training=true, Agt# v Adv#=2v22022.10 | -2.51 | 1.7 | |
| CURIO_teamPartial observability=true, Decentralized training=true, Agt# v Adv#=2v22022.10 | -3.57 | 1.75 | |
| SPARSEPartial observability=true, Decentralized training=true, Agt# v Adv#=2v22022.10 | -4.72 | 2.4 | |
| CURIO_selfPartial observability=true, Decentralized training=true, Agt# v Adv#=2v22022.10 | -6.5 | 2.18 | |
| ELIGN_selfPartial observability=true, Decentralized training=true, Agt# v Adv#=2v22022.10 | -7.58 | 2.55 | |
| ELIGN_teamPartial observability=true, Decentralized training=true, Agt# v Adv#=2v22022.10 | -7.69 | 2.69 |