Reinforcement Learning Surrogate Modeling on Swimmer (S) (test)
101Reward RatioCubist
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CubistMNR=110, Model Size=2761±802026.07 | 101 | 0.036 | |
| Decision TreeMD=10, Model Size=2384±862026.07 | 95 | 0.058 | |
| ORCAIDMD=2, Model Size=62±32026.07 | 90 | 0.059 | |
| RuleFitMNR=14, Model Size=109±52026.07 | 87 | 0.065 |