Adversarial linear mixture MDPs
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Dynamic Regret Minimization | Adversarial linear mixture MDPs with unknown transition and full-information feedback | Metric- | 0 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Dynamic Regret Minimization | Adversarial linear mixture MDPs with unknown transition and full-information feedback | Metric- | 0 |