MPE World
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-agent Offline Reinforcement Learning | MPE World Expert | Score135.2 | 16 | |
| Multi-agent Reinforcement Learning | MPE World v1 (Expert) | Normalized Score119.7 | 10 | |
| Multi-Agent Reinforcement Learning | MPE World Medium Replay | Mean Episode Return65.9 | 8 | |
| Offline Multi-Agent Reinforcement Learning | MPE World (Medium) | Average Normalized Score104.9 | 8 | |
| Multi-agent Offline Reinforcement Learning | MPE World Medium | Score0.938 | 8 | |
| Multi-agent Offline Reinforcement Learning | MPE World (Medium-replay) | Score73.4 | 8 | |
| Multi-agent Offline Reinforcement Learning | MPE World (Random) | Score68 | 8 | |
| Multi-Agent Reinforcement Learning | MPE World Medium Expert | Normalized Score89.4 | 4 | |
| Multi-Agent Reinforcement Learning | MPE World Medium | Normalized Score84.5 | 4 | |
| Multi-Agent Reinforcement Learning | MPE World Random Medium | Normalized Score42.7 | 4 | |
| Multi-Agent Reinforcement Learning | MPE World Expert | Mean Episode Return91.8 | 4 | |
| Multi-Agent Reinforcement Learning | MPE World Medium Expert | Mean Episode Return79.9 | 4 | |
| Multi-Agent Reinforcement Learning | MPE World Medium | Mean Episode Return57.5 | 4 | |
| Multi-Agent Reinforcement Learning | MPE World Random Medium | Mean Episode Return30.3 | 4 | |
| Multi-Agent Reinforcement Learning | MPE World (Random) | Mean Episode Return35.6 | 4 | |
| Multi-agent Reinforcement Learning | MPE World Medium v1 | Normalized Score0.938 | 4 | |
| Multi-agent Reinforcement Learning | MPE World v1 (Med-Rep) | Normalized Score73.4 | 4 | |
| Multi-agent Reinforcement Learning | MPE World v1 (Random) | Normalized Score68 | 4 | |
| Multi-Agent Reinforcement Learning | MPE World | Score (Random)40 | 3 |
Showing 19 of 19 rows