# Model-free learning on Toy 3-arm MDP

Source: [Model-free learning on Toy 3-arm MDP](<https://www.sota2.com/research/sota/model-free-learning-on-toy-3-arm-mdp>)

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

Data updated: 2026-03-20T08:03:07.061Z

Evaluation of model-free reinforcement learning algorithms specifically on the Toy 3-arm MDP environment, focusing on regret bounds and time dependence.

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 | Model-free learning |
| Dataset (including any stated split) | Toy 3-arm MDP |
| Metric | Regret (T-dependence) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 1 of 1 |
| 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 (T-dependence)](<https://www.sota2.com/research/sota/model-free-learning-on-toy-3-arm-mdp.md?metric=Regret%20(T-dependence)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Regret (T-dependence) | Result date | Report paper |
| --- | --- | --- | --- |
| Dig-DEC | 1 | Not recorded | 68fa7bfe1e209131cea8bbc3 |

### Dig-DEC

Regret (T-dependence): 1. Result ID: 69bcfd7047f34ce924a6d167.

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

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

Recorded evaluation configuration: {"Exploration Mechanism":"information gain"}. This record does not assert independent reproduction.

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