Reinforcement Learning on BDCL
78.78Scaled Mean RewardReversedQ
Evaluation results
| Method | Links | |
|---|---|---|
| ReversedQPolicy=ReversedQ2026.05 | 78.78 | |
| RandomizedQ-UpdatePolicy=RandomizedQ-Update2026.05 | 57.44 | |
| RandomizedQ-InitPolicy=RandomizedQ-Init2026.05 | 47.36 | |
| RandomizedQ-BackwardPolicy=RandomizedQ-Backward2026.05 | 21.55 | |
| RandomizedQPolicy=RandomizedQ2026.05 | 9.53 |