POMDP Planning on Modified LightDark 1D
6.095Mean ReturnPOMCPOW
Evaluation results
| Method | Links | ||
|---|---|---|---|
| POMCPOWNumber of simulation steps=10-step, Number of episodes=1002026.05 | 6.095 | 0.3008 | |
| Voro-POMCPOWNumber of simulation steps=10-step, Number of episodes=1002026.05 | 6.0367 | 0.2731 |