# Regret Bound Estimation on Hybrid MDPs (Bilinear or Coverable, Bellman Complete, On-Policy)

Source: [Regret Bound Estimation on Hybrid MDPs (Bilinear or Coverable, Bellman Complete, On-Policy)](<https://www.sota2.com/research/sota/regret-bound-estimation-on-hybrid-mdps-bilinear-or-coverable-bellman-complete-on-policy>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-20T08:03:06.996Z

Evaluation of theoretical regret bounds for algorithms operating in Hybrid Markov Decision Processes (MDPs) characterized by Bilinear or Coverable dynamics, Bellman Completeness, and an On-Policy setting.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Regret Bound Estimation |
| Dataset (including any stated split) | Hybrid MDPs {Bilinear or Coverable} + Bellman Complete + On-Policy setting |
| Metric | Regret Bound (On-Policy) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Regret Bound (On-Policy)](<https://www.sota2.com/research/sota/regret-bound-estimation-on-hybrid-mdps-bilinear-or-coverable-bellman-complete-on-policy.md?metric=Regret%20Bound%20(On-Policy)>): Lower is better; unit: SCALAR.

- [Regret T-Dependence](<https://www.sota2.com/research/sota/regret-bound-estimation-on-hybrid-mdps-bilinear-or-coverable-bellman-complete-on-policy.md?metric=Regret%20T-Dependence>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Regret Bound (On-Policy) | Result date | Report paper |
| --- | --- | --- | --- |
| Dig-DEC | 3 | Not recorded | 68fa7bfe1e209131cea8bbc3 |

### Dig-DEC

Regret Bound (On-Policy): 3. Result ID: 69bcfd7047f34ce924a6d15f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfe1e209131cea8bbc3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfe1e209131cea8bbc3.md>)

Recorded evaluation configuration: {"Model-Free":"✓","Bandit Feedback":"✓","General Reward":"✗"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
