# Inverse Reinforcement Learning on Dataset 3

Source: [Inverse Reinforcement Learning on Dataset 3](<https://www.sota2.com/research/sota/inverse-reinforcement-learning-on-dataset-3>)

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

Data updated: 2026-03-05T08:34:48.382Z

Evaluation of Inverse Reinforcement Learning performance on Dataset 3, typically measured using Mean Squared Error (MSE).

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 | Inverse Reinforcement Learning |
| Dataset (including any stated split) | Dataset 3 |
| Metric | MSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 13 of 13 |
| 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

- [MSE](<https://www.sota2.com/research/sota/inverse-reinforcement-learning-on-dataset-3.md?metric=MSE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | MSE | Result date | Report paper |
| --- | --- | --- | --- |
| AIRL | 0 | Not recorded | 68fa7c541e209131cea8d959 |
| MAYA | 2.6 | Not recorded | 68fa7c541e209131cea8d959 |
| GLM | 3.1 | Not recorded | 68fa7c541e209131cea8d959 |
| GLM | 3.1 | Not recorded | 68fa7c541e209131cea8d959 |
| MAYA | 3.7 | Not recorded | 68fa7c541e209131cea8d959 |
| BC | 5.5 | Not recorded | 68fa7c541e209131cea8d959 |
| MAYA | 5.7 | Not recorded | 68fa7c541e209131cea8d959 |
| Dagger | 21.6 | Not recorded | 68fa7c541e209131cea8d959 |
| SQIL | 22.6 | Not recorded | 68fa7c541e209131cea8d959 |
| GAIL | 27.5 | Not recorded | 68fa7c541e209131cea8d959 |
| DBR | 41.38 | Not recorded | 68fa7c541e209131cea8d959 |
| Pref-Comp | 125.7 | Not recorded | 68fa7c541e209131cea8d959 |
| MCE | 140.3 | Not recorded | 68fa7c541e209131cea8d959 |

### AIRL

MSE: 0. Result ID: 69a940156dbb7075b952b46b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64bf1e209131cea063e7.md>)

[Implementation](<https://sites.google.com/view/adversarial-irl>)

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

### MAYA

MSE: 2.6. Result ID: 69a940156dbb7075b952b474.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

Recorded evaluation configuration: {"Divergence Metric":"Wasserstein","tau":"7"}. This record does not assert independent reproduction.

### GLM

MSE: 3.1. Result ID: 69a940156dbb7075b952b471.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

Recorded evaluation configuration: {"Context":"no"}. This record does not assert independent reproduction.

### GLM

MSE: 3.1. Result ID: 69a940156dbb7075b952b472.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

Recorded evaluation configuration: {"Context":"yes"}. This record does not assert independent reproduction.

### MAYA

MSE: 3.7. Result ID: 69a940156dbb7075b952b473.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

Recorded evaluation configuration: {"Divergence Metric":"KL","tau":"7"}. This record does not assert independent reproduction.

### BC

MSE: 5.5. Result ID: 69a940156dbb7075b952b46a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5cac1e209131ce9d325b.md>)

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

### MAYA

MSE: 5.7. Result ID: 69a940156dbb7075b952b475.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

Recorded evaluation configuration: {"Divergence Metric":"DTW","tau":"7"}. This record does not assert independent reproduction.

### Dagger

MSE: 21.6. Result ID: 69a940156dbb7075b952b46c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61c81e209131ce9f5cc2.md>)

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

### SQIL

MSE: 22.6. Result ID: 69a940156dbb7075b952b470.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66781e209131cea105b4.md>)

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

### GAIL

MSE: 27.5. Result ID: 69a940156dbb7075b952b469.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62821e209131ce9f9b65.md>)

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

### DBR

MSE: 41.38. Result ID: 69a940156dbb7075b952b46d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d21e209131cea532d0.md>)

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

### Pref-Comp

MSE: 125.7. Result ID: 69a940156dbb7075b952b46f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8d1e209131cea408c8.md>)

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

### MCE

MSE: 140.3. Result ID: 69a940156dbb7075b952b46e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c541e209131cea8d959.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.
