halfcheetah
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Offline Reinforcement Learning | 1T10S HalfCheetah Medium | Score61.447 | 53 | |
| Continuous Robot Control | HalfCheetah v3 (test) | Reward11,767 | 48 | |
| Offline Reinforcement Learning | HalfCheetah 1T10S (Medium-Replay) | Return57.835 | 44 | |
| Reinforcement Learning | Halfcheetah v5 | Average Return13,996.2 | 43 | |
| Offline Reinforcement Learning | halfcheetah medium-replay | Normalized Score68.4 | 43 | |
| Offline Reinforcement Learning | halfcheetah medium | Normalized Score68.2 | 43 | |
| Reinforcement Learning | HalfCheetah v3 | Mean Reward17,177 | 34 | |
| Offline Reinforcement Learning | Halfcheetah D4RL v2 (offline) | Average Score56 | 32 | |
| Offline Reinforcement Learning | halfcheetah medium v2 | Average Score4,452 | 27 | |
| Offline Reinforcement Learning | 1T10S HalfCheetah (Medium-Expert) | Score89.22 | 26 | |
| Offline Reinforcement Learning | halfcheetah Mixed Dataset | Normalized Reward74.5 | 24 | |
| Reinforcement Learning | HalfCheetah | Average Return7,223.53 | 22 | |
| Offline Reinforcement Learning | HalfCheetah BodyMass Shift (Medium-Expert) | Average Return76.533 | 18 | |
| Offline Reinforcement Learning | HalfCheetah BodyMass Shift (Medium-Replay) | Average Return42.405 | 18 | |
| Offline Reinforcement Learning | HalfCheetah JointNoise Shift (Medium) | Average Return56.213 | 18 | |
| Offline Reinforcement Learning | HalfCheetah BodyMass Shift (Medium) | Average Return47.303 | 18 | |
| Offline Reinforcement Learning | HalfCheetah Medium-Expert 1T10S | Average Return83.692 | 18 | |
| Offline Reinforcement Learning | halfcheetah medium-expert v2 | Normalized Score108.1 | 18 | |
| Offline Reinforcement Learning | HalfCheetah Medium-Expert Gym-MuJoCo D4RL | Normalized Score95.1 | 18 | |
| Offline Reinforcement Learning | HalfCheetah kinematic shifts | Score79.6 | 16 | |
| Offline Reinforcement Learning | HalfCheetah Gym-MuJoCo Medium-Replay D4RL | Normalized Score48.9 | 16 | |
| Offline Reinforcement Learning | Halfcheetah | Average Return7,357.5 | 16 | |
| Offline Reinforcement Learning | HalfCheetah medium-expert | Normalized Score107.6 | 15 | |
| Offline Reinforcement Learning | halfcheetah medium-replay v2 | Normalized Score51.2 | 14 | |
| Cross-Domain Offline Policy Adaptation | halfcheetah med Source Target | Normalized Score69.7 | 14 |
Showing 25 of 126 rows