MaMuJoCo
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-Agent Offline Reinforcement Learning | MaMuJoCo 2HalfCheetah Medium | Performance4,554.11 | 9 | |
| Multi-Agent Reinforcement Learning | MAMuJoCo Walker2d 6x1 (test) | Average Episodic Return28.56 | 8 | |
| Multi-Agent Reinforcement Learning | MAMuJoCo Ant 8x1 (test) | Average Episodic Return45.06 | 8 | |
| Multi-Agent Reinforcement Learning | MAMuJoCo Hopper 3x1 (test) | Average Episodic Return31.02 | 8 | |
| Multi-Agent Reinforcement Learning | MAMuJoCo HalfCheetah 6x1 (test) | Average Episodic Return43.1 | 8 | |
| Multi-agent continuous control | MaMuJoCo HalfCheetah Expert v2 | Score118.5 | 8 | |
| Multi-agent continuous control | MaMuJoCo HalfCheetah v2 (Med-rep) | Score59.5 | 8 | |
| Multi-agent continuous control | MaMuJoCo HalfCheetah v2 (Random) | Score39.7 | 8 | |
| Offline Multi-Agent Reinforcement Learning | MaMuJoCo Half-C (Random) | Average Normalized Score43.8 | 7 | |
| Offline Multi-Agent Reinforcement Learning | MaMuJoCo Half-C (Medium-Replay) | Average Normalized Score73.1 | 7 | |
| Offline Multi-Agent Reinforcement Learning | MaMuJoCo Half-C Medium | Avg Normalized Score81.3 | 7 | |
| Offline Multi-Agent Reinforcement Learning | MaMuJoCo Half-C Expert | Average Normalized Score118.5 | 7 | |
| Multi-agent Reinforcement Learning | MaMuJoCo OMIGA 2-Ant (Medium) | Average Episode Reward1,619 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo OMIGA 2-Ant (Medium-Replay) | Average Episode Reward1,105.13 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo OMIGA 2-Ant (Medium-Expert) | Average Episode Reward2,002 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo OMIGA 2-Ant (Expert) | Average Episode Reward2,191 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo OMIGA 3-Hopper (Medium) | Average Episode Reward3,360 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo OMIGA 3-Hopper (Medium-Expert) | Average Episode Reward3,568 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo (OMIGA) 3-Hopper (Expert) | Average Episode Reward3,595 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo (OMIGA) 6-HalfCheetah Medium | Average Episode Reward4,695 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo OMIGA 6-HalfCheetah (Medium-Replay) | Avg Episode Reward4,582 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo OMIGA 6-HalfCheetah (Medium-Expert) | Average Episode Reward5,237 | 6 | |
| Multi-agent Reinforcement Learning | MaMuJoCo OMIGA 6-HalfCheetah (Expert) | Average Episode Reward5,545 | 6 | |
| Offline Multi-agent Reinforcement Learning | MaMuJoCo 2-HalfCheetah (Random) | Average Return39.7 | 6 | |
| Offline Multi-agent Reinforcement Learning | MaMuJoCo 2-HalfCheetah (Med-Replay) | Average Return78.9 | 6 |
Showing 25 of 38 rows