Multi-agent MuJoCo Hopper
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Offline Multi-Agent Reinforcement Learning | Multi-agent MuJoCo Hopper expert, medium, medium-replay, medium-expert | Return3,621 | 12 | |
| Robotic Control | Multi-agent MuJoCo Hopper medium | Average Return1,189.26 | 5 | |
| Robotic Control | Multi-agent MuJoCo Hopper HAPPO collected (expert) | Average Return859.63 | 5 |
Showing 3 of 3 rows