Reinforcement Learning on Gymnasium LunarLander
280.9ReturnASAP
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ASAPRL Algorithm=SAC2026.01 | 280.9 | — | 18.5 | |
| SAC BaseRL Algorithm=SAC2026.01 | 279.2 | — | 28.9 | |
| CAPSRL Algorithm=SAC2026.01 | 251 | — | 25.9 | |
| GRADRL Algorithm=SAC2026.01 | 250.9 | — | 24.8 | |
| L2C2RL Algorithm=SAC2026.01 | 249.3 | — | 34.9 | |
| ASAPBase RL Algorithm=PPO2026.01 | 200.7 | 22.1 | — | |
| L2C2Base RL Algorithm=PPO2026.01 | 197.6 | 29.2 | — | |
| GRADBase RL Algorithm=PPO2026.01 | 188 | 29.8 | — | |
| CAPSBase RL Algorithm=PPO2026.01 | 187.1 | 24.6 | — | |
| PPO BaseBase RL Algorithm=PPO2026.01 | 172.8 | 30.9 | — |