# Offline Goal-Conditioned Reinforcement Learning on D'ClawTurn (offline)

Source: [Offline Goal-Conditioned Reinforcement Learning on D'ClawTurn (offline)](<https://www.sota2.com/research/sota/offline-goal-conditioned-reinforcement-learning-on-d-clawturn-offline>)

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

Data updated: 2026-02-26T05:41:09.592Z

Evaluation of Offline Goal-Conditioned Reinforcement Learning performance using the D'ClawTurn (offline) dataset, measured by metrics such as Discounted Return.

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 | Offline Goal-Conditioned Reinforcement Learning |
| Dataset (including any stated split) | D'ClawTurn (offline) |
| Metric | Discounted Return |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Discounted Return](<https://www.sota2.com/research/sota/offline-goal-conditioned-reinforcement-learning-on-d-clawturn-offline.md?metric=Discounted%20Return>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Discounted Return | Result date | Report paper |
| --- | --- | --- | --- |
| GoFAR | 9.34 | Not recorded | 68fa6de41e209131cea3cb23 |
| AM | 2.82 | Not recorded | 68fa6de41e209131cea3cb23 |
| WGCSL | 0 | Not recorded | 68fa6de41e209131cea3cb23 |
| GCSL | 0 | Not recorded | 68fa6de41e209131cea3cb23 |
| DDPG | 0 | Not recorded | 68fa6de41e209131cea3cb23 |

### GoFAR

Discounted Return: 9.34. Result ID: 698fee053a6c314849fcdae6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de41e209131cea3cb23.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6de41e209131cea3cb23.md>)

[Implementation](<https://jasonma2016.github.io/GoFAR/>)

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

### AM

Discounted Return: 2.82. Result ID: 698fee053a6c314849fcdae9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de41e209131cea3cb23.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea261ff.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Actor-Critic","HER rate":"1.0"}. This record does not assert independent reproduction.

### WGCSL

Discounted Return: 0. Result ID: 698fee053a6c314849fcdae7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de41e209131cea3cb23.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bdb1e209131cea30a41.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Supervised Learning","HER rate":"1.0"}. This record does not assert independent reproduction.

### GCSL

Discounted Return: 0. Result ID: 698fee053a6c314849fcdae8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de41e209131cea3cb23.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686f1e209131cea1c316.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Supervised Learning","HER rate":"1.0"}. This record does not assert independent reproduction.

### DDPG

Discounted Return: 0. Result ID: 698fee053a6c314849fcdaea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6de41e209131cea3cb23.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64131e209131cea0293b.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Actor-Critic","HER rate":"0.2"}. This record does not assert independent reproduction.

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