D4RL Walker
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Offline Reinforcement Learning | D4RL Walker Medium | Reward77.84 | 10 | |
| Offline-to-online Reinforcement Learning | D4RL Walker expert discretized | Online Normalized Score14.8 | 9 | |
| Offline-to-online Reinforcement Learning | D4RL Walker medium discretized | Online Normalised Score15.9 | 9 | |
| Locomotion | D4RL Walker Random | Mean Return50.4 | 5 | |
| Reinforcement Learning | D4RL Walker Medium-Expert | Mean Normalized Return100 | 5 | |
| Reinforcement Learning | D4RL Walker Random | Mean Normalized Return47.1 | 5 | |
| Reinforcement Learning | D4RL Walker no right thigh (medium) | Mean Return3,293 | 4 | |
| Reinforcement Learning | D4RL Walker broken right thigh (medium) | Mean Return3,743 | 4 | |
| Reinforcement Learning | D4RL Walker Med-Expert | D4RL Score110.51 | 2 | |
| Reinforcement Learning | D4RL Walker Med-Replay | D4RL Score72.36 | 2 |
Showing 10 of 10 rows