| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| PushT | Picard | Time (s)0.71 | 14 | 1mo ago | |
| MimicGen (1000 demonstrations) | EfficientFlow | Success Rate81.99 | 8 | 1mo ago | |
| MimicGen 200 demonstrations | EfficientFlow | Success Rate70.26 | 8 | 1mo ago | |
| MimicGen 100 demonstrations | EfficientFlow | Avg Success Rate54.18 | 8 | 1mo ago | |
| Humanoid v4 | MA-MPPI | Local Optima Escape Rate72.3 | 7 | 23d ago | |
| HalfCheetah v4 | MA-MPPI | Local Optima Escape Rate76.8 | 7 | 23d ago | |
| BipedalWalker v3 | MA-MPPI | Local Optima Escape Rate83.5 | 7 | 23d ago | |
| Pendulum v1 | MA-MPPI | Local Optima Escape Rate89.2 | 7 | 23d ago | |
| Robotic Control Inference Benchmark | Inference Time (ms)90 | 6 | 18d ago | ||
| Ant P-FLK | MSAC | Maximum Average Return2,922.37 | 6 | 25d ago | |
| Ant MDP | SAC | Max Average Return5,614.1 | 6 | 25d ago | |
| Half Cheetah | DGCRL | AP-3.58 | 6 | 1mo ago | |
| Ant | DGCRL | AP80.25 | 6 | 1mo ago | |
| Hopper | DGCRL | AP93.85 | 6 | 1mo ago | |
| Hopper V | GRU-ODE | Average Return1,545,104 | 6 | 1mo ago | |
| Walker V | GRU-ODE | Average Return61,227 | 6 | 1mo ago | |
| Walker-P | RMF | Average Return1,123,176 | 6 | 1mo ago | |
| Ant-V | RMF | Average Return1,021,165 | 6 | 1mo ago | |
| Ant-P | SLAC | Average Return950,129 | 6 | 1mo ago | |
| Multi-agent MuJoCo HalfCheetah (medium-expert) | BCQ-MA | Average Return3,543.7 | 5 | 1mo ago | |
| Multi-agent MuJoCo HalfCheetah (medium-replay) | OMIGA | Average Return2,504.7 | 5 | 1mo ago | |
| Multi-agent MuJoCo HalfCheetah (medium) | OMIGA | Average Return3,608.13 | 5 | 1mo ago | |
| Multi-agent MuJoCo HalfCheetah (expert) | OMIGA | Average Return3,383.61 | 5 | 1mo ago | |
| Multi-agent MuJoCo Ant (medium-expert) | OMIGA | Average Return1,720.33 | 5 | 1mo ago | |
| Multi-agent MuJoCo Ant (medium-replay) | OMIGA | Avg Return1,105.13 | 5 | 1mo ago |
