# Reward Conditioning (RC) on Maze2D (test)

Source: [Reward Conditioning (RC) on Maze2D (test)](<https://www.sota2.com/research/sota/reward-conditioning-rc-on-maze2d-test>)

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

Data updated: 2026-02-26T06:02:15.736Z

Evaluation of Reward Conditioning performance on the test split of the Maze2D environment.

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 | Reward Conditioning (RC) |
| Dataset (including any stated split) | Maze2D (test) |
| Metric | Reward |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Reward](<https://www.sota2.com/research/sota/reward-conditioning-rc-on-maze2d-test.md?metric=Reward>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Reward | Result date | Report paper |
| --- | --- | --- | --- |
| Uni\[MASK\] - multi-task + finetune | 2.74 | Not recorded | 68fa6df81e209131cea3d0fd |
| Uni\[MASK\] - finetune | 2.73 | Not recorded | 68fa6df81e209131cea3d0fd |
| Decision-GPT | 2.73 | Not recorded | 68fa6df81e209131cea3d0fd |
| Uni\[MASK\] - multi-task (BC & RC) | 2.68 | Not recorded | 68fa6df81e209131cea3d0fd |
| Uni\[MASK\] - single-task | 2.64 | Not recorded | 68fa6df81e209131cea3d0fd |
| Uni\[MASK\] - finetune | 2.61 | Not recorded | 68fa6df81e209131cea3d0fd |
| Uni\[MASK\] - multi-task + finetune | 2.42 | Not recorded | 68fa6df81e209131cea3d0fd |
| Uni\[MASK\] - single-task | 2.41 | Not recorded | 68fa6df81e209131cea3d0fd |
| Uni\[MASK\] - multi-task (BC & RC) | 2.39 | Not recorded | 68fa6df81e209131cea3d0fd |
| Decision-GPT | 2.32 | Not recorded | 68fa6df81e209131cea3d0fd |
| Uni\[MASK\] - random-mask | 2.31 | Not recorded | 68fa6df81e209131cea3d0fd |
| Uni\[MASK\] - random-mask | 2.2 | Not recorded | 68fa6df81e209131cea3d0fd |
| Feedforward Neural Network | 1.88 | Not recorded | 68fa6df81e209131cea3d0fd |
| Decision Transformer | 1.7 | Not recorded | 68fa6df81e209131cea3d0fd |
| Feedforward Neural Network | 1.53 | Not recorded | 68fa6df81e209131cea3d0fd |
| Decision Transformer | 1.49 | Not recorded | 68fa6df81e209131cea3d0fd |

### Uni\[MASK\] - multi-task + finetune

Reward: 2.74. Result ID: 698ff0293a6c314849fcebd9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":5}. This record does not assert independent reproduction.

### Uni\[MASK\] - finetune

Reward: 2.73. Result ID: 698ff0293a6c314849fcebdb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":5}. This record does not assert independent reproduction.

### Decision-GPT

Reward: 2.73. Result ID: 698ff0293a6c314849fcebe6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":10}. This record does not assert independent reproduction.

### Uni\[MASK\] - multi-task (BC & RC)

Reward: 2.68. Result ID: 698ff0293a6c314849fcebd8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":5}. This record does not assert independent reproduction.

### Uni\[MASK\] - single-task

Reward: 2.64. Result ID: 698ff0293a6c314849fcebd7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":5}. This record does not assert independent reproduction.

### Uni\[MASK\] - finetune

Reward: 2.61. Result ID: 698ff0293a6c314849fcebe3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":10}. This record does not assert independent reproduction.

### Uni\[MASK\] - multi-task + finetune

Reward: 2.42. Result ID: 698ff0293a6c314849fcebe1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":10}. This record does not assert independent reproduction.

### Uni\[MASK\] - single-task

Reward: 2.41. Result ID: 698ff0293a6c314849fcebdf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":10}. This record does not assert independent reproduction.

### Uni\[MASK\] - multi-task (BC & RC)

Reward: 2.39. Result ID: 698ff0293a6c314849fcebe0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":10}. This record does not assert independent reproduction.

### Decision-GPT

Reward: 2.32. Result ID: 698ff0293a6c314849fcebde.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":5}. This record does not assert independent reproduction.

### Uni\[MASK\] - random-mask

Reward: 2.31. Result ID: 698ff0293a6c314849fcebe2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":10}. This record does not assert independent reproduction.

### Uni\[MASK\] - random-mask

Reward: 2.2. Result ID: 698ff0293a6c314849fcebda.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Implementation](<https://github.com/micahcarroll/uniMASK>)

Recorded evaluation configuration: {"Context Length":5}. This record does not assert independent reproduction.

### Feedforward Neural Network

Reward: 1.88. Result ID: 698ff0293a6c314849fcebe4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

Recorded evaluation configuration: {"Context Length":10}. This record does not assert independent reproduction.

### Decision Transformer

Reward: 1.7. Result ID: 698ff0293a6c314849fcebe5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b46.md>)

Recorded evaluation configuration: {"Context Length":10}. This record does not assert independent reproduction.

### Feedforward Neural Network

Reward: 1.53. Result ID: 698ff0293a6c314849fcebdc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

Recorded evaluation configuration: {"Context Length":5}. This record does not assert independent reproduction.

### Decision Transformer

Reward: 1.49. Result ID: 698ff0293a6c314849fcebdd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6df81e209131cea3d0fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b46.md>)

Recorded evaluation configuration: {"Context Length":5}. This record does not assert independent reproduction.

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