# Operational Throughput Optimization on Internal Learned Simulators (held-out shifts)

Source: [Operational Throughput Optimization on Internal Learned Simulators (held-out shifts)](<https://www.sota2.com/research/sota/operational-throughput-optimization-on-internal-learned-simulators-held-out-shifts>)

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

Data updated: 2026-03-27T12:31:09.466Z

Evaluation of performance optimization strategies focused on operational throughput, measured by improvement percentages and confidence intervals, using internal learned simulators tested on held-out shifts.

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 | Operational Throughput Optimization |
| Dataset (including any stated split) | Internal Learned Simulators (held-out shifts) |
| Metric | Throughput Improvement (%) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Throughput Improvement (%)](<https://www.sota2.com/research/sota/operational-throughput-optimization-on-internal-learned-simulators-held-out-shifts.md?metric=Throughput%20Improvement%20(%25)>): Higher is better; unit: PERCENT.

- [95% CI (Throughput Improvement)](<https://www.sota2.com/research/sota/operational-throughput-optimization-on-internal-learned-simulators-held-out-shifts.md?metric=95%25%20CI%20(Throughput%20Improvement)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Throughput Improvement (%) | Result date | Report paper |
| --- | --- | --- | --- |
| Offline Actor-Critic | 2.4 | Not recorded | 69c60ee90636e5bf4afc83b6 |
| Fine-Tuned Behavior Cloning | 2.1 | Not recorded | 69c60ee90636e5bf4afc83b6 |
| Behavior Cloning | 1.6 | Not recorded | 69c60ee90636e5bf4afc83b6 |
| Human Decisions (replayed) | 0 | Not recorded | 69c60ee90636e5bf4afc83b6 |

### Offline Actor-Critic

Throughput Improvement (%): 2.4. Result ID: 69c6787d47f34ce924b04a58.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee90636e5bf4afc83b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60ee90636e5bf4afc83b6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Fine-Tuned Behavior Cloning

Throughput Improvement (%): 2.1. Result ID: 69c6787d47f34ce924b04a59.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee90636e5bf4afc83b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60ee90636e5bf4afc83b6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Behavior Cloning

Throughput Improvement (%): 1.6. Result ID: 69c6787d47f34ce924b04a5a.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee90636e5bf4afc83b6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Human Decisions (replayed)

Throughput Improvement (%): 0. Result ID: 69c6787d47f34ce924b04a5b.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee90636e5bf4afc83b6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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