Optimal Policy Search on GridWorld (Varying Gamma)
8Iterations (gamma=0.9)PI
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PI2024.09 | 8 | 9 | 8 | |
| PMD (Euc-Agg)projection=Euclidean Aggressive2024.09 | 18 | 20 | 24 | |
| PMD (Euc)projection=Euclidean2024.09 | 208 | 2,002 | 18,122 |
| Method | Links | |||
|---|---|---|---|---|
| PI2024.09 | 8 | 9 | 8 | |
| PMD (Euc-Agg)projection=Euclidean Aggressive2024.09 | 18 | 20 | 24 | |
| PMD (Euc)projection=Euclidean2024.09 | 208 | 2,002 | 18,122 |