POMDP Planning on Light Dark (D, D, C)
61.1Mean RewardPOMCPD
Evaluation results
| Method | Links | |
|---|---|---|
| POMCPDNumber of simulations=1000, Discretization=true2017.09 | 61.1 | |
| PFT-DPWNumber of simulations=1000, Discretization=false2017.09 | 57.2 | |
| POMCPOWNumber of simulations=1000, Discretization=false2017.09 | 56.1 | |
| DESPOTDNumber of simulations=1000, Discretization=true2017.09 | 54.2 | |
| POMCP-DPWNumber of simulations=10002017.09 | 7.3 | |
| DESPOTNumber of simulations=1000, Discretization=false2017.09 | 6.8 | |
| QMDPNumber of simulations=10002017.09 | 6.4 |