Multi-Agent MuJoCo
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-Agent Reinforcement Learning | Multi-Agent MuJoCo HalfCheetah fore thigh | Average Score8,347 | 12 | |
| Multi-Agent Reinforcement Learning | Multi-Agent MuJoCo HalfCheetah fore shin | Average Evaluation Score4,373 | 12 | |
| Multi-Agent Reinforcement Learning | Multi-Agent MuJoCo HalfCheetah fore foot | Average Evaluation Score6,054 | 12 | |
| Multi-Agent Reinforcement Learning | Multi-Agent MuJoCo HalfCheetah back thigh | Avg Score7,460 | 12 | |
| Multi-Agent Reinforcement Learning | Multi-Agent MuJoCo HalfCheetah back shin | Average Return7,176 | 12 | |
| Multi-Agent Reinforcement Learning | Multi-Agent MuJoCo HalfCheetah back foot | Average Score5,646 | 12 | |
| Offline Multi-Agent Reinforcement Learning | Multi-agent MuJoCo Swimmer (e, m1, m2, e-m1, e-m2, m1-m2) | Return430.7 | 5 | |
| Offline Multi-Agent Reinforcement Learning | Multi-agent MuJoCo HalfCheetah expert, medium, medium-replay, medium-expert | Return5,413.7 | 5 | |
| Offline Multi-Agent Reinforcement Learning | Multi-agent MuJoCo Ant expert, medium, medium-replay, medium-expert | Return2,162.8 | 5 | |
| Robotic Control | Multi-agent MuJoCo HalfCheetah (medium-expert) | Average Return3,543.7 | 5 | |
| Robotic Control | Multi-agent MuJoCo HalfCheetah (medium-replay) | Average Return2,504.7 | 5 | |
| Robotic Control | Multi-agent MuJoCo HalfCheetah (medium) | Average Return3,608.13 | 5 | |
| Robotic Control | Multi-agent MuJoCo HalfCheetah (expert) | Average Return3,383.61 | 5 | |
| Robotic Control | Multi-agent MuJoCo Ant (medium-expert) | Average Return1,720.33 | 5 | |
| Robotic Control | Multi-agent MuJoCo Ant (medium-replay) | Avg Return1,105.13 | 5 | |
| Robotic Control | Multi-agent MuJoCo Ant (medium) | Avg Return1,418.44 | 5 | |
| Robotic Control | Multi-agent MuJoCo Ant (expert) | Average Return2,055.46 | 5 | |
| Robotic Control | Multi-agent MuJoCo Hopper (medium-expert) | Average Return709 | 5 | |
| Robotic Control | Multi-agent MuJoCo Hopper (medium-replay) | Average Return774.18 | 5 | |
| Offline Multi-Agent Reinforcement Learning | Multi-agent MuJoCo HalfCheetah k=1 (e, m1, m2, e-m1, e-m2, m1-m2) | Return3,760.5 | 4 |
Showing 20 of 20 rows