Policy Evaluation on Cart-Pole off-policy perfect features
0.17MSEBBO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BBO2021.06 | 0.17 | — | |
| LSTD+2021.06 | 0.17 | — | |
| TD2021.06 | 0.57 | — | |
| LSTD2021.06 | 1.38 | — | |
| BRM2021.06 | 1.95 | — | |
| TDC2021.06 | 2.1 | — | |
| GTD22021.06 | 4.04 | — | |
| BBOPolicy Type=off-policy, Feature Type=perfect2021.06 | — | 24.58 | |
| BRMPolicy Type=off-policy, Feature Type=perfect2021.06 | — | 122.12 | |
| GTD2Policy Type=off-policy, Feature Type=perfect2021.06 | — | 267.92 | |
| LSTDPolicy Type=off-policy, Feature Type=perfect2021.06 | — | 681.19 | |
| LSTD+Policy Type=off-policy, Feature Type=perfect2021.06 | — | 24.57 | |
| TDPolicy Type=off-policy, Feature Type=perfect2021.06 | — | 67.91 | |
| TDCPolicy Type=off-policy, Feature Type=perfect2021.06 | — | 159.23 |