Reinforcement Learning Surrogate Modeling on LunarLander (LL) (test)
90Reward RatioORCAID
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ORCAIDMD=4, Model Size=316±52026.07 | 90 | 71 | |
| CubistMNR=50, Model Size=1161±92026.07 | 88 | 64 | |
| RuleFitMNR=21, Model Size=137±102026.07 | 79 | 100 | |
| Decision TreeMD=14, Model Size=4099±752026.07 | 39 | 102 |