# Mean Field Team Games competition on Battlefield 4x4 grid

Source: [Mean Field Team Games competition on Battlefield 4x4 grid](<https://www.sota2.com/research/sota/mean-field-team-games-competition-on-battlefield-4x4-grid>)

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

Data updated: 2026-02-26T05:36:21.652Z

Evaluation of model performance on the Mean Field Team Games competition conducted on the Battlefield 4x4 grid environment, typically measured by Average Reward.

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 | Mean Field Team Games competition |
| Dataset (including any stated split) | Battlefield 4x4 grid |
| Metric | Avg Reward |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 25 of 25 |
| 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

- [Avg Reward](<https://www.sota2.com/research/sota/mean-field-team-games-competition-on-battlefield-4x4-grid.md?metric=Avg%20Reward>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Avg Reward | Result date | Report paper |
| --- | --- | --- | --- |
| MF-MAPPO | 86.26 | Not recorded | 68fa7ba11e209131cea89785 |
| MF-MAPPO | 86.22 | Not recorded | 68fa7ba11e209131cea89785 |
| MF-MAPPO | 85.95 | Not recorded | 68fa7ba11e209131cea89785 |
| MF-MAPPO | 82.58 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-CC | 77.21 | Not recorded | 68fa7ba11e209131cea89785 |
| MF-MAPPO | 76.26 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-PS | 75.14 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-PS | 73.85 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-PS | 72.78 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-CC | 71.64 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-CC | 70.6 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-PS | 68.81 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-CC | 65.58 | Not recorded | 68fa7ba11e209131cea89785 |
| MF-IPPO | 65.26 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-CC | 62 | Not recorded | 68fa7ba11e209131cea89785 |
| MF-IPPO | 61.54 | Not recorded | 68fa7ba11e209131cea89785 |
| MF-IPPO | 55.82 | Not recorded | 68fa7ba11e209131cea89785 |
| MAPPO-PS | 54.43 | Not recorded | 68fa7ba11e209131cea89785 |
| MF-IPPO | 51.6 | Not recorded | 68fa7ba11e209131cea89785 |
| MF-IPPO | 36.1 | Not recorded | 68fa7ba11e209131cea89785 |
| DDPG-MFTG | 0 | Not recorded | 68fa7ba11e209131cea89785 |
| DDPG-MFTG | 0 | Not recorded | 68fa7ba11e209131cea89785 |
| DDPG-MFTG | 0 | Not recorded | 68fa7ba11e209131cea89785 |
| DDPG-MFTG | 0 | Not recorded | 68fa7ba11e209131cea89785 |
| DDPG-MFTG | 0 | Not recorded | 68fa7ba11e209131cea89785 |

### MF-MAPPO

Avg Reward: 86.26. Result ID: 699a4af75698665ec4d26f85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-IPPO"}. This record does not assert independent reproduction.

### MF-MAPPO

Avg Reward: 86.22. Result ID: 699a4af75698665ec4d26f8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-PS"}. This record does not assert independent reproduction.

### MF-MAPPO

Avg Reward: 85.95. Result ID: 699a4af75698665ec4d26f94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"DDPG-MFTG"}. This record does not assert independent reproduction.

### MF-MAPPO

Avg Reward: 82.58. Result ID: 699a4af75698665ec4d26f8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-CC"}. This record does not assert independent reproduction.

### MAPPO-CC

Avg Reward: 77.21. Result ID: 699a4af75698665ec4d26f92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"DDPG-MFTG"}. This record does not assert independent reproduction.

### MF-MAPPO

Avg Reward: 76.26. Result ID: 699a4af75698665ec4d26f99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-MAPPO"}. This record does not assert independent reproduction.

### MAPPO-PS

Avg Reward: 75.14. Result ID: 699a4af75698665ec4d26f91.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"DDPG-MFTG"}. This record does not assert independent reproduction.

### MAPPO-PS

Avg Reward: 73.85. Result ID: 699a4af75698665ec4d26f82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-IPPO"}. This record does not assert independent reproduction.

### MAPPO-PS

Avg Reward: 72.78. Result ID: 699a4af75698665ec4d26f87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-PS"}. This record does not assert independent reproduction.

### MAPPO-CC

Avg Reward: 71.64. Result ID: 699a4af75698665ec4d26f88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-PS"}. This record does not assert independent reproduction.

### MAPPO-CC

Avg Reward: 70.6. Result ID: 699a4af75698665ec4d26f83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-IPPO"}. This record does not assert independent reproduction.

### MAPPO-PS

Avg Reward: 68.81. Result ID: 699a4af75698665ec4d26f8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-CC"}. This record does not assert independent reproduction.

### MAPPO-CC

Avg Reward: 65.58. Result ID: 699a4af75698665ec4d26f8d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-CC"}. This record does not assert independent reproduction.

### MF-IPPO

Avg Reward: 65.26. Result ID: 699a4af75698665ec4d26f90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"DDPG-MFTG"}. This record does not assert independent reproduction.

### MAPPO-CC

Avg Reward: 62. Result ID: 699a4af75698665ec4d26f97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-MAPPO"}. This record does not assert independent reproduction.

### MF-IPPO

Avg Reward: 61.54. Result ID: 699a4af75698665ec4d26f81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-IPPO"}. This record does not assert independent reproduction.

### MF-IPPO

Avg Reward: 55.82. Result ID: 699a4af75698665ec4d26f86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-PS"}. This record does not assert independent reproduction.

### MAPPO-PS

Avg Reward: 54.43. Result ID: 699a4af75698665ec4d26f96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-MAPPO"}. This record does not assert independent reproduction.

### MF-IPPO

Avg Reward: 51.6. Result ID: 699a4af75698665ec4d26f8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-CC"}. This record does not assert independent reproduction.

### MF-IPPO

Avg Reward: 36.1. Result ID: 699a4af75698665ec4d26f95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

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

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

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-MAPPO"}. This record does not assert independent reproduction.

### DDPG-MFTG

Avg Reward: 0. Result ID: 699a4af75698665ec4d26f84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5dee1e209131ce9ddf2e.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-IPPO"}. This record does not assert independent reproduction.

### DDPG-MFTG

Avg Reward: 0. Result ID: 699a4af75698665ec4d26f89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5dee1e209131ce9ddf2e.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-PS"}. This record does not assert independent reproduction.

### DDPG-MFTG

Avg Reward: 0. Result ID: 699a4af75698665ec4d26f8e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5dee1e209131ce9ddf2e.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"MAPPO-CC"}. This record does not assert independent reproduction.

### DDPG-MFTG

Avg Reward: 0. Result ID: 699a4af75698665ec4d26f93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5dee1e209131ce9ddf2e.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"DDPG-MFTG"}. This record does not assert independent reproduction.

### DDPG-MFTG

Avg Reward: 0. Result ID: 699a4af75698665ec4d26f98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89785.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5dee1e209131ce9ddf2e.md>)

Recorded evaluation configuration: {"Opponent Red Team Policy":"MF-MAPPO"}. This record does not assert independent reproduction.

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