# Preference-conditioned control on OpenCDA-MARL CARLA Competitive

Source: [Preference-conditioned control on OpenCDA-MARL CARLA Competitive](<https://www.sota2.com/research/sota/preference-conditioned-control-on-opencda-marl-carla-competitive>)

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

Data updated: 2026-06-15T08:08:52.160Z

Evaluation of control policies conditioned on human preferences within the OpenCDA MARL Competitive environment, assessed using metrics like Utility, Success Rate, Collision Rate, and Throughput.

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 control |
| Dataset (including any stated split) | OpenCDA-MARL CARLA Competitive |
| Metric | Utility |
| Unit | SCALAR |
| Direction | Higher 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

- [Utility](<https://www.sota2.com/research/sota/preference-conditioned-control-on-opencda-marl-carla-competitive.md?metric=Utility>): Higher is better; unit: SCALAR.

- [Success Rate](<https://www.sota2.com/research/sota/preference-conditioned-control-on-opencda-marl-carla-competitive.md?metric=Success%20Rate>): Higher is better; unit: PERCENT.

- [Collision Rate](<https://www.sota2.com/research/sota/preference-conditioned-control-on-opencda-marl-carla-competitive.md?metric=Collision%20Rate>): Lower is better; unit: PERCENT.

- [Throughput](<https://www.sota2.com/research/sota/preference-conditioned-control-on-opencda-marl-carla-competitive.md?metric=Throughput>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Utility | Result date | Report paper |
| --- | --- | --- | --- |
| PCMA | -2877.1 | Not recorded | 6a2f873ed33dfb23e783c1d1 |
| SAC | -5084.5 | Not recorded | 6a2f873ed33dfb23e783c1d1 |
| MAPPO | -13660.2 | Not recorded | 6a2f873ed33dfb23e783c1d1 |

### PCMA

Utility: -2877.1. Result ID: 6a2fb233fbc373592c2be5ad.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873ed33dfb23e783c1d1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2f873ed33dfb23e783c1d1.md>)

Recorded evaluation configuration: {"Backbone":"PCMA"}. This record does not assert independent reproduction.

### SAC

Utility: -5084.5. Result ID: 6a2fb233fbc373592c2be5ab.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873ed33dfb23e783c1d1.md>)

Recorded evaluation configuration: {"Backbone":"SAC"}. This record does not assert independent reproduction.

### MAPPO

Utility: -13660.2. Result ID: 6a2fb233fbc373592c2be5ac.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873ed33dfb23e783c1d1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ddd1e209131cea3c8e0.md>)

[Implementation](<https://github.com/marlbenchmark/on-policy>)

Recorded evaluation configuration: {"Backbone":"MAPPO"}. This record does not assert independent reproduction.

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