Non-Stationary Reinforcement Learning on Isaac Gym Non-Stationary
1.13nAUC (Steady)SAC+AES
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| SAC+AESBase RL Algorithm=SAC, Entropy Scheduling (AES)=true2026.01 | 1.13 | 0.73 | 0.93 | 0.95 | 0.79 | 0 | 0.35 | 0.18 | 0.16 | 0.3 | |
| MEow+AESBase RL Algorithm=MEow, Entropy Scheduling (AES)=true2026.01 | 1.09 | 0.81 | 0.9 | 0.99 | 0.92 | 0 | 0.26 | 0.17 | 0.09 | 0.16 | |
| SACBase RL Algorithm=SAC, Entropy Scheduling (AES)=false2026.01 | 1 | 0.58 | 0.69 | 0.57 | 0.51 | 0 | 0.42 | 0.31 | 0.43 | 0.49 | |
| MEowBase RL Algorithm=MEow, Entropy Scheduling (AES)=false2026.01 | 0.99 | 0.68 | 0.76 | 0.76 | 0.54 | 0 | 0.31 | 0.23 | 0.23 | 0.45 | |
| PPO+AESBase RL Algorithm=PPO, Entropy Scheduling (AES)=true2026.01 | 0.87 | 0.62 | 0.67 | 0.7 | 0.57 | 0 | 0.29 | 0.23 | 0.2 | 0.34 | |
| PPOBase RL Algorithm=PPO, Entropy Scheduling (AES)=false2026.01 | 0.82 | 0.44 | 0.59 | 0.55 | 0.48 | 0 | 0.46 | 0.28 | 0.33 | 0.41 | |
| SQL+AESBase RL Algorithm=SQL, Entropy Scheduling (AES)=true2026.01 | 0.81 | 0.66 | 0.66 | 0.72 | 0.6 | 0 | 0.19 | 0.19 | 0.11 | 0.26 | |
| SQLBase RL Algorithm=SQL, Entropy Scheduling (AES)=false2026.01 | 0.76 | 0.39 | 0.47 | 0.49 | 0.38 | 0 | 0.49 | 0.38 | 0.36 | 0.5 |