# Offline Reinforcement Learning on D4RL Adroit pen human v0

Source: [Offline Reinforcement Learning on D4RL Adroit pen human v0](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-adroit-pen-human-v0>)

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

Data updated: 2026-02-26T05:53:45.650Z

Evaluation of Offline Reinforcement Learning performance specifically on the D4RL Adroit 'pen human' environment configuration (v0), typically measured by Normalized average 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 Reinforcement Learning |
| Dataset (including any stated split) | D4RL Adroit pen human v0 |
| Metric | Normalized Return |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [Normalized Return](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-adroit-pen-human-v0.md?metric=Normalized%20Return>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Normalized Return | Result date | Report paper |
| --- | --- | --- | --- |
| DPPO | 76.3 | Not recorded | 68fa71091e209131cea4eca7 |
| CQL | 55.8 | Not recorded | 68fa6aec1e209131cea2b133 |
| PT+IQL | 53 | Not recorded | 68fa71091e209131cea4eca7 |
| EDAC | 52.1 | Not recorded | 68fa6aec1e209131cea2b133 |
| CQL | 35.2 | Not recorded | 68fa6aec1e209131cea2b133 |
| PT+CQL | 31.6 | Not recorded | 68fa71091e209131cea4eca7 |
| BC | 25.8 | Not recorded | 68fa6aec1e209131cea2b133 |
| PT+%BC | 19.4 | Not recorded | 68fa71091e209131cea4eca7 |
| SAC-N | 9.5 | Not recorded | 68fa6aec1e209131cea2b133 |
| REM | 5.4 | Not recorded | 68fa6aec1e209131cea2b133 |
| SAC | 4.3 | Not recorded | 68fa6aec1e209131cea2b133 |
| PT+RvS | -1.8 | Not recorded | 68fa71091e209131cea4eca7 |

### DPPO

Normalized Return: 76.3. Result ID: 69918eee3a6c31484908f8fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4eca7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4eca7.md>)

[Implementation](<https://github.com/snu-mllab/DPPO>)

Recorded evaluation configuration: {"Framework":"Preference Transformer (PT)"}. This record does not assert independent reproduction.

### CQL

Normalized Return: 55.8. Result ID: 698e41bbffc3901de09c11f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6c2.md>)

Recorded evaluation configuration: {"Implementation Source":"Paper"}. This record does not assert independent reproduction.

### PT+IQL

Normalized Return: 53. Result ID: 69918eee3a6c31484908f8f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4eca7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea4136d.md>)

Recorded evaluation configuration: {"Framework":"Preference Transformer (PT)"}. This record does not assert independent reproduction.

### EDAC

Normalized Return: 52.1. Result ID: 698e41bbffc3901de09c11f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

Recorded evaluation configuration: {"Implementation Source":"Ours"}. This record does not assert independent reproduction.

### CQL

Normalized Return: 35.2. Result ID: 698e41bbffc3901de09c11f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6c2.md>)

Recorded evaluation configuration: {"Implementation Source":"Reproduced"}. This record does not assert independent reproduction.

### PT+CQL

Normalized Return: 31.6. Result ID: 69918eee3a6c31484908f8f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4eca7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea4136d.md>)

Recorded evaluation configuration: {"Framework":"Preference Transformer (PT)"}. This record does not assert independent reproduction.

### BC

Normalized Return: 25.8. Result ID: 698e41bbffc3901de09c11ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

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

### PT+%BC

Normalized Return: 19.4. Result ID: 69918eee3a6c31484908f8f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4eca7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea4136d.md>)

Recorded evaluation configuration: {"Framework":"Preference Transformer (PT)"}. This record does not assert independent reproduction.

### SAC-N

Normalized Return: 9.5. Result ID: 698e41bbffc3901de09c11f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

Recorded evaluation configuration: {"Implementation Source":"Ours"}. This record does not assert independent reproduction.

### REM

Normalized Return: 5.4. Result ID: 698e41bbffc3901de09c11f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d41e209131cea1e72a.md>)

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

### SAC

Normalized Return: 4.3. Result ID: 698e41bbffc3901de09c11f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64a51e209131cea05d13.md>)

[Implementation](<https://www.sota2.com/github.com/haarnoja/sac>)

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

### PT+RvS

Normalized Return: -1.8. Result ID: 69918eee3a6c31484908f8f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4eca7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea3485c.md>)

Recorded evaluation configuration: {"Framework":"Preference Transformer (PT)"}. This record does not assert independent reproduction.

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