# Multi-Agent Reinforcement Learning on SMAC protoss\_8v8 v2 (test)

Source: [Multi-Agent Reinforcement Learning on SMAC protoss\_8v8 v2 (test)](<https://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-smac-protoss_8v8-v2-test>)

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

Data updated: 2026-05-19T10:12:10.556Z

Evaluation of Multi-Agent Reinforcement Learning performance on the specific SMAC scenario 'protoss\_8v8' (version 2, test split), typically measured by Win Rate (WR) and Area Under the Curve (AUC).

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 | Multi-Agent Reinforcement Learning |
| Dataset (including any stated split) | SMAC protoss\_8v8 v2 (test) |
| Metric | Win Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Win Rate](<https://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-smac-protoss_8v8-v2-test.md?metric=Win%20Rate>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-smac-protoss_8v8-v2-test.md?metric=AUC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Win Rate | Result date | Report paper |
| --- | --- | --- | --- |
| HIBCG | 44.8 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| ExpoComm | 43.3 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| MAGI | 39.3 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| AIB-only | 37.4 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| CommFormer | 36.3 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| GACG | 35.8 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| HIB-flat | 35.5 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| BVME | 33.3 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| QMIX | 32.8 | Not recorded | 6a0bee9ddbc836b87d82c492 |

### HIBCG

Win Rate: 44.8. Result ID: 6a0c36bafbc373592c02db87.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

Recorded evaluation configuration: {"config":"AIB+XIB+GP"}. This record does not assert independent reproduction.

### ExpoComm

Win Rate: 43.3. Result ID: 6a0c36bafbc373592c02db82.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa772e1e209131cea719f9.md>)

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

### MAGI

Win Rate: 39.3. Result ID: 6a0c36bafbc373592c02db80.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

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

### AIB-only

Win Rate: 37.4. Result ID: 6a0c36bafbc373592c02db85.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

Recorded evaluation configuration: {"config":"structural IB"}. This record does not assert independent reproduction.

### CommFormer

Win Rate: 36.3. Result ID: 6a0c36bafbc373592c02db81.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73351e209131cea5b287.md>)

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

### GACG

Win Rate: 35.8. Result ID: 6a0c36bafbc373592c02db83.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73271e209131cea5ab8a.md>)

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

### HIB-flat

Win Rate: 35.5. Result ID: 6a0c36bafbc373592c02db86.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

Recorded evaluation configuration: {"config":"AIB+XIB, flat"}. This record does not assert independent reproduction.

### BVME

Win Rate: 33.3. Result ID: 6a0c36bafbc373592c02db84.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

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

### QMIX

Win Rate: 32.8. Result ID: 6a0c36bafbc373592c02db7f.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9ddbc836b87d82c492.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64671e209131cea046e9.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.
