Infinite-horizon Average-Reward RL on Unichain CMDPs
0Constraint ViolationAgarwal et al.
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Agarwal et al.Param.=Tabular, Ergodic?=Yes, Constr.?=Yes2026.02 | 0 | — | |
| Wei et al.Param.=Tabular, Ergodic?=No, Constr.?=Yes2026.02 | 0 | — |