LTL-guided Reinforcement Learning on Letter Infinite-horizon (test)
7.13µAccSEMLTL
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SEMLTLTask Specification Type=SMALL, |Q|=7, |δ|=162026.02 | 7.13 | 4.76 | |
| DEEPLTLTask Specification Type=SMALL, |Q|=7, |δ|=162026.02 | 6.15 | — | |
| SEMLTLTask Specification Type=ALWAYS-REACTIVE[5, 1], |Q|=38, |δ|=2042026.02 | 3.06 | 7.06 | |
| SEMLTLTask Specification Type=COMPLEX-PATROL[5, 5], |Q|=49, |δ|=2272026.02 | 1.83 | 6.44 | |
| DEEPLTLTask Specification Type=COMPLEX-PATROL[5, 5], |Q|=49, |δ|=2272026.02 | 1.78 | — |