Continuous Control on MuJoCo Ant (Abrupt-change recovery time)
5.9Recovery Time (%)MEow+AES
Evaluation results
| Method | Links | |
|---|---|---|
| MEow+AESBase RL Algorithm=MEow, Entropy Scheduling (AES)=Enabled2026.01 | 5.9 | |
| SAC+AESBase RL Algorithm=SAC, Entropy Scheduling (AES)=Enabled2026.01 | 6.7 | |
| PPO+AESBase RL Algorithm=PPO, Entropy Scheduling (AES)=Enabled2026.01 | 6.9 | |
| MEow+AESBase RL Algorithm=MEow, Entropy Scheduling (AES)=Enabled2026.01 | 7 | |
| SQL+AESBase RL Algorithm=SQL, Entropy Scheduling (AES)=Enabled2026.01 | 8.3 | |
| SAC+AESBase RL Algorithm=SAC, Entropy Scheduling (AES)=Enabled2026.01 | 8.7 | |
| PPO+AESBase RL Algorithm=PPO, Entropy Scheduling (AES)=Enabled2026.01 | 9.7 | |
| SQL+AESBase RL Algorithm=SQL, Entropy Scheduling (AES)=Enabled2026.01 | 10.2 | |
| PPOBase RL Algorithm=PPO, Entropy Scheduling (AES)=Disabled2026.01 | 10.9 | |
| PPOBase RL Algorithm=PPO, Entropy Scheduling (AES)=Disabled2026.01 | 11.2 | |
| MEowBase RL Algorithm=MEow, Entropy Scheduling (AES)=Disabled2026.01 | 11.6 | |
| MEowBase RL Algorithm=MEow, Entropy Scheduling (AES)=Disabled2026.01 | 11.7 | |
| SACBase RL Algorithm=SAC, Entropy Scheduling (AES)=Disabled2026.01 | 11.9 | |
| SACBase RL Algorithm=SAC, Entropy Scheduling (AES)=Disabled2026.01 | 14.1 | |
| SQLBase RL Algorithm=SQL, Entropy Scheduling (AES)=Disabled2026.01 | 16.4 | |
| SQLBase RL Algorithm=SQL, Entropy Scheduling (AES)=Disabled2026.01 | 17.5 |