Reinforcement Learning Surrogate Modeling on Reacher (R) (test)
81Reward RatioCubist
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CubistMNR=150, Model Size=4820±472026.07 | 81 | 0.002 | |
| ORCAIDMD=4, Model Size=457±22026.07 | 80 | 0.003 | |
| Decision TreeMD=16, Model Size=3328±342026.07 | 56 | 0.007 | |
| RuleFitMNR=30, Model Size=212±62026.07 | 42 | 0.008 |