# Regret Bound Estimation on Hybrid MDPs Bilinear setting

Source: [Regret Bound Estimation on Hybrid MDPs Bilinear setting](<https://www.sota2.com/research/sota/regret-bound-estimation-on-hybrid-mdps-bilinear-setting>)

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

Data updated: 2026-03-20T08:03:06.967Z

Evaluation of algorithms for estimating regret bounds (both on-policy and off-policy) within the context of Hybrid Markov Decision Processes (MDPs) configured for a Bilinear 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 setting |
| Metric | Off-Policy Regret Bound |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

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

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

## Recorded results

| Method | Off-Policy Regret Bound | Result date | Report paper |
| --- | --- | --- | --- |
| Liu et al. (2025) | 2 | Not recorded | 68fa7bfe1e209131cea8bbc3 |
| Liu et al. (2025) | 5 | Not recorded | 68fa7bfe1e209131cea8bbc3 |
| Dig-DEC | 13 | Not recorded | 68fa7bfe1e209131cea8bbc3 |

### Liu et al. (2025)

Off-Policy Regret Bound: 2. Result ID: 69bcfd7047f34ce924a6d15c.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa785f1e209131cea780ea.md>)

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

### Liu et al. (2025)

Off-Policy Regret Bound: 5. Result ID: 69bcfd7047f34ce924a6d15d.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa785f1e209131cea780ea.md>)

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

### Dig-DEC

Off-Policy Regret Bound: 13. Result ID: 69bcfd7047f34ce924a6d15e.

[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.
