# Value function estimation on Matrix Game B v1 (test)

Source: [Value function estimation on Matrix Game B v1 (test)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test>)

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

Data updated: 2026-03-23T11:54:44.901Z

Evaluation of Q-function estimation performance on the test split of the Matrix Game B v1 dataset, measured by specific Q-value metrics (Q1, Q2, Q\_tot).

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 | Value function estimation |
| Dataset (including any stated split) | Matrix Game B v1 (test) |
| Metric | Q1 Value (A) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Q1 Value (A)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q1%20Value%20(A)>): Higher is better; unit: SCALAR.

- [Q1 Value (B)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q1%20Value%20(B)>): Higher is better; unit: SCALAR.

- [Q1 Value (C)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q1%20Value%20(C)>): Higher is better; unit: SCALAR.

- [Q2 Value (A)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q2%20Value%20(A)>): Higher is better; unit: SCALAR.

- [Q2 Value (B)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q2%20Value%20(B)>): Higher is better; unit: SCALAR.

- [Q2 Value (C)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q2%20Value%20(C)>): Higher is better; unit: SCALAR.

- [Q\_tot (A, A)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q_tot%20(A%2C%20A)>): Higher is better; unit: SCALAR.

- [Q\_tot (A, B)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q_tot%20(A%2C%20B)>): Higher is better; unit: SCALAR.

- [Q\_tot (A, C)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q_tot%20(A%2C%20C)>): Higher is better; unit: SCALAR.

- [Q\_tot (B, A)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q_tot%20(B%2C%20A)>): Higher is better; unit: SCALAR.

- [Q\_tot (B, B)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q_tot%20(B%2C%20B)>): Higher is better; unit: SCALAR.

- [Q\_tot (B, C)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q_tot%20(B%2C%20C)>): Higher is better; unit: SCALAR.

- [Q\_tot (C, A)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q_tot%20(C%2C%20A)>): Higher is better; unit: SCALAR.

- [Q\_tot (C, B)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q_tot%20(C%2C%20B)>): Higher is better; unit: SCALAR.

- [Q\_tot (C, C)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Q_tot%20(C%2C%20C)>): Higher is better; unit: SCALAR.

- [Joint Value (Q\_tot)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Joint%20Value%20(Q_tot)>): Higher is better; unit: SCALAR.

- [Agent Utility (Q\_i)](<https://www.sota2.com/research/sota/value-function-estimation-on-matrix-game-b-v1-test.md?metric=Agent%20Utility%20(Q_i)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Q1 Value (A) | Result date | Report paper |
| --- | --- | --- | --- |
| Unconstrained QMIX | 6.2 | Not recorded | 6916b7940052cac1dc65e0b0 |
| QTRAN | 4 | Not recorded | 6916b7940052cac1dc65e0b0 |
| QPLEX | 0.4 | Not recorded | 6916b7940052cac1dc65e0b0 |
| QMIX | -0.6 | Not recorded | 6916b7940052cac1dc65e0b0 |

### Unconstrained QMIX

Q1 Value (A): 6.2. Result ID: 69c129f947f34ce924a9cdaf.

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

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

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

### QTRAN

Q1 Value (A): 4. Result ID: 69c129f947f34ce924a9cdb2.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa65bc1e209131cea0c014.md>)

[Implementation](<https://github.com/Sonkyunghwan/QTRAN>)

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

### QPLEX

Q1 Value (A): 0.4. Result ID: 69c129f947f34ce924a9cdb1.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af31e209131cea2b551.md>)

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

### QMIX

Q1 Value (A): -0.6. Result ID: 69c129f947f34ce924a9cdb0.

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