Optimal Policy Search on Taxi
2Iterations (gamma=0.9)TRPO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TRPO2024.09 | 2 | 2 | 3 | |
| PMD (Euc-Agg)projection=Euclidean Aggressive2024.09 | 4 | 33 | 20 | |
| PMD (Euc)projection=Euclidean2024.09 | 4 | 52 | 68 | |
| PI2024.09 | 16 | 20 | 17 | |
| REINFORCE2024.09 | 4,265 | 7,278 | — |