# Matrix Game on Game A

Source: [Matrix Game on Game A](<https://www.sota2.com/research/sota/matrix-game-on-game-a>)

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

Data updated: 2026-03-23T11:54:45.000Z

Evaluation of model performance on the Game A matrix game, focusing on estimating joint payoffs and individual Q-values.

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 | Matrix Game |
| Dataset (including any stated split) | Game A |
| Metric | Joint Payoff Estimate |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Joint Payoff Estimate](<https://www.sota2.com/research/sota/matrix-game-on-game-a.md?metric=Joint%20Payoff%20Estimate>): Higher is better; unit: SCALAR.

- [Individual Q-Value Estimate](<https://www.sota2.com/research/sota/matrix-game-on-game-a.md?metric=Individual%20Q-Value%20Estimate>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Joint Payoff Estimate | Result date | Report paper |
| --- | --- | --- | --- |
| Non-Monotonic QMIX | 12 | Not recorded | 6916b7940052cac1dc65e0b0 |
| QMIX | -12 | Not recorded | 6916b7940052cac1dc65e0b0 |

### Non-Monotonic QMIX

Joint Payoff Estimate: 12. Result ID: 69c129f947f34ce924a9cdd7.

[Reporting paper](<https://www.sota2.com/research/paper/6916b7940052cac1dc65e0b0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6916b7940052cac1dc65e0b0.md>)

Recorded evaluation configuration: {"update-style":"SARSA-style","factorization":"non-monotonic","exploration strategy":"ε-greedy"}. This record does not assert independent reproduction.

### QMIX

Joint Payoff Estimate: -12. Result ID: 69c129f947f34ce924a9cdd8.

[Reporting paper](<https://www.sota2.com/research/paper/6916b7940052cac1dc65e0b0.md>)

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

Recorded evaluation configuration: {"update-style":"SARSA-style","factorization":"monotonic","exploration strategy":"ε-greedy"}. This record does not assert independent reproduction.

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