# Multi-agent Reinforcement Learning on SMAC MMM2 v1 (test)

Source: [Multi-agent Reinforcement Learning on SMAC MMM2 v1 (test)](<https://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-smac-mmm2-v1-test>)

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

Data updated: 2026-05-19T10:12:10.379Z

Evaluation of Multi-Agent Reinforcement Learning performance on the test split of the SMAC MMM2 v1 environment, typically measured by Test Win Rate.

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 MMM2 v1 (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-mmm2-v1-test.md?metric=Win%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Win Rate | Result date | Report paper |
| --- | --- | --- | --- |
| HIBCG | 81.4 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| CommFormer | 77.4 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| BVME | 75.5 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| HIB-flat | 54.2 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| MAGI | 52.8 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| AIB-only | 50.2 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| GACG | 48.8 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| QMIX | 38.6 | Not recorded | 6a0bee9ddbc836b87d82c492 |
| ExpoComm | 20.4 | Not recorded | 6a0bee9ddbc836b87d82c492 |

### HIBCG

Win Rate: 81.4. Result ID: 6a0c36bafbc373592c02db5a.

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

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

Recorded evaluation configuration: {"Unit Composition":"3-type","Training Budget":"2M"}. This record does not assert independent reproduction.

### CommFormer

Win Rate: 77.4. Result ID: 6a0c36bafbc373592c02db54.

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

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

Recorded evaluation configuration: {"Unit Composition":"3-type","Training Budget":"2M"}. This record does not assert independent reproduction.

### BVME

Win Rate: 75.5. Result ID: 6a0c36bafbc373592c02db57.

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

Recorded evaluation configuration: {"Unit Composition":"3-type","Training Budget":"2M"}. This record does not assert independent reproduction.

### HIB-flat

Win Rate: 54.2. Result ID: 6a0c36bafbc373592c02db59.

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

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

Recorded evaluation configuration: {"Unit Composition":"3-type","Training Budget":"2M"}. This record does not assert independent reproduction.

### MAGI

Win Rate: 52.8. Result ID: 6a0c36bafbc373592c02db53.

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

Recorded evaluation configuration: {"Unit Composition":"3-type","Training Budget":"2M"}. This record does not assert independent reproduction.

### AIB-only

Win Rate: 50.2. Result ID: 6a0c36bafbc373592c02db58.

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

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

Recorded evaluation configuration: {"Unit Composition":"3-type","Training Budget":"2M"}. This record does not assert independent reproduction.

### GACG

Win Rate: 48.8. Result ID: 6a0c36bafbc373592c02db56.

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

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

Recorded evaluation configuration: {"Unit Composition":"3-type","Training Budget":"2M"}. This record does not assert independent reproduction.

### QMIX

Win Rate: 38.6. Result ID: 6a0c36bafbc373592c02db52.

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

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

Recorded evaluation configuration: {"Unit Composition":"3-type","Training Budget":"2M"}. This record does not assert independent reproduction.

### ExpoComm

Win Rate: 20.4. Result ID: 6a0c36bafbc373592c02db55.

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

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

Recorded evaluation configuration: {"Unit Composition":"3-type","Training Budget":"2M"}. This record does not assert independent reproduction.

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