neorl
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Locomotion | NeoRL HalfCheetah-Medium | Mean Normalized Score81.1 | 19 | |
| Locomotion | NeoRL Hopper-Low | Mean Normalized Score30.7 | 19 | |
| Locomotion | NeoRL Walker2d High | Mean Normalized Score82.2 | 18 | |
| Reinforcement Learning | NeoRL halfcheetah-low | Normalized Score54.7 | 14 | |
| Locomotion | NeoRL Hopper Medium | Mean Normalized Score104.3 | 12 | |
| Locomotion | NeoRL HalfCheetah Low | Mean Normalized Score58.5 | 12 | |
| Locomotion | NeoRL Hopper High | Mean Normalized Score107.7 | 11 | |
| Offline Reinforcement Learning | NeoRL2 SafetyHalfCheetah | Average Normalized Performance73.56 | 8 | |
| Offline Reinforcement Learning | NeoRL2 RocketRecovery | Normalized Performance Score83.2 | 8 | |
| Hopper | NeoRL Hopper-H high quality | Normalized Score65.9 | 7 | |
| Hopper | NeoRL Hopper-M medium quality | Normalized Score58.1 | 7 | |
| Offline Reinforcement Learning | NeoRL (test) | Hopper High Score100.5 | 7 | |
| Reinforcement Learning | neorl halfcheetah high | Normalized Score84 | 7 | |
| Reinforcement Learning | neorl hopper high | Normalized Score87.8 | 7 | |
| Reinforcement Learning | neorl walker2d-medium | Normalized Score70.1 | 7 | |
| Reinforcement Learning | neorl halfcheetah-medium | Normalized Score0.778 | 7 | |
| Reinforcement Learning | NeoRL hopper medium | Normalized Score70.3 | 7 | |
| Reinforcement Learning | neorl hopper-low | Normalized Score22.3 | 7 |
Showing 18 of 18 rows