# Preference-conditioned Autonomous Highway Navigation on Highway-Env Lane 3 Specialist

Source: [Preference-conditioned Autonomous Highway Navigation on Highway-Env Lane 3 Specialist](<https://www.sota2.com/research/sota/preference-conditioned-autonomous-highway-navigation-on-highway-env-lane-3-specialist>)

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

Data updated: 2026-06-18T07:32:31.250Z

Evaluation of autonomous highway navigation performance under preference conditioning using the Highway-Env Lane 3 Specialist configuration, reporting Reward, Episode Length, and Lane 3 adherence metrics.

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 | Preference-conditioned Autonomous Highway Navigation |
| Dataset (including any stated split) | Highway-Env Lane 3 Specialist |
| Metric | Reward |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Reward](<https://www.sota2.com/research/sota/preference-conditioned-autonomous-highway-navigation-on-highway-env-lane-3-specialist.md?metric=Reward>): Higher is better; unit: SCALAR.

- [Episode Length](<https://www.sota2.com/research/sota/preference-conditioned-autonomous-highway-navigation-on-highway-env-lane-3-specialist.md?metric=Episode%20Length>): Higher is better; unit: SCALAR.

- [Lane 3 Adherence (Abs)](<https://www.sota2.com/research/sota/preference-conditioned-autonomous-highway-navigation-on-highway-env-lane-3-specialist.md?metric=Lane%203%20Adherence%20(Abs)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Reward | Result date | Report paper |
| --- | --- | --- | --- |
| GRID | 34.9 | Not recorded | 6a337bb3206542251d7c5118 |
| Wrong Specialist | 34 | Not recorded | 6a337bb3206542251d7c5118 |
| BC | 29.9 | Not recorded | 6a337bb3206542251d7c5118 |
| AIRL | 24.3 | Not recorded | 6a337bb3206542251d7c5118 |
| Right Specialist | 22.1 | Not recorded | 6a337bb3206542251d7c5118 |

### GRID

Reward: 34.9. Result ID: 6a339f07fbc373592c308c1d.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bb3206542251d7c5118.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bb3206542251d7c5118.md>)

Recorded evaluation configuration: {"Mode":"Specialist"}. This record does not assert independent reproduction.

### Wrong Specialist

Reward: 34. Result ID: 6a339f07fbc373592c308c1a.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bb3206542251d7c5118.md>)

Recorded evaluation configuration: {"Mode":"Specialist"}. This record does not assert independent reproduction.

### BC

Reward: 29.9. Result ID: 6a339f07fbc373592c308c1b.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bb3206542251d7c5118.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64631e209131cea04425.md>)

Recorded evaluation configuration: {"Mode":"Specialist"}. This record does not assert independent reproduction.

### AIRL

Reward: 24.3. Result ID: 6a339f07fbc373592c308c1c.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bb3206542251d7c5118.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64bf1e209131cea063e7.md>)

[Implementation](<https://sites.google.com/view/adversarial-irl>)

Recorded evaluation configuration: {"Mode":"Specialist"}. This record does not assert independent reproduction.

### Right Specialist

Reward: 22.1. Result ID: 6a339f07fbc373592c308c19.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bb3206542251d7c5118.md>)

Recorded evaluation configuration: {"Mode":"Specialist"}. This record does not assert independent reproduction.

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