POMDP Planning on RockSample (7, 8)
21.57Expected ReturnSARSOP*
Evaluation results
| Method | Links | |
|---|---|---|
| SARSOP*|S|=12, 544, |A|=13, |Z|=3, Number of runs=5, Simulations per run=10^52025.11 | 21.57 | |
| POMCGS|S|=12, 544, |A|=13, |Z|=3, Number of runs=5, Simulations per run=10^52025.11 | 20.17 | |
| NVI|S|=12, 544, |A|=13, |Z|=3, Number of runs=5, Simulations per run=10^52025.11 | 18.95 | |
| MCVI|S|=12, 544, |A|=13, |Z|=3, Number of runs=5, Simulations per run=10^52025.11 | 17.34 | |
| Recurrent PPO|S|=12, 544, |A|=13, |Z|=3, Number of runs=5, Simulations per run=10^52025.11 | 7.73 |