# Offline Reinforcement Learning on D4RL Adroit pen v0 (cloned)

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

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

Data updated: 2026-02-26T05:53:42.017Z

Evaluation of Offline Reinforcement Learning performance specifically on the D4RL Adroit 'pen' environment configuration using the cloned v0 dataset.

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 v0 (cloned) |
| Metric | Normalized Avg Return |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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 Avg Return](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-adroit-pen-v0-cloned.md?metric=Normalized%20Avg%20Return>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Normalized Avg Return | Result date | Report paper |
| --- | --- | --- | --- |
| DPPO | 75.1 | Not recorded | 68fa71091e209131cea4eca7 |
| EDAC | 68.2 | Not recorded | 68fa6aec1e209131cea2b133 |
| Easy BCQ | 67 | Not recorded | 68fa6b631e209131cea2df51 |
| SAC-N | 64.1 | Not recorded | 68fa6aec1e209131cea2b133 |
| Fu et al. | 56.9 | Not recorded | 68fa6b631e209131cea2df51 |
| Rev. KL Reg. | 55.3 | Not recorded | 68fa6b631e209131cea2df51 |
| Exp. Weight | 54.7 | Not recorded | 68fa6b631e209131cea2df51 |
| BC | 49.3 | Not recorded | 68fa6b631e209131cea2df51 |
| PT+IQL | 42.9 | Not recorded | 68fa71091e209131cea4eca7 |
| CQL | 40.3 | Not recorded | 68fa6aec1e209131cea2b133 |
| BC | 38.3 | Not recorded | 68fa6aec1e209131cea2b133 |
| PT+%BC | 37.4 | Not recorded | 68fa71091e209131cea4eca7 |
| CQL | 27.2 | Not recorded | 68fa6aec1e209131cea2b133 |
| PT+CQL | 18.3 | Not recorded | 68fa71091e209131cea4eca7 |
| SAC | -0.8 | Not recorded | 68fa6aec1e209131cea2b133 |
| REM | -1 | Not recorded | 68fa6aec1e209131cea2b133 |
| PT+RvS | -2.2 | Not recorded | 68fa71091e209131cea4eca7 |

### DPPO

Normalized Avg Return: 75.1. Result ID: 69918eee3a6c31484908f8ff.

[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.

### EDAC

Normalized Avg Return: 68.2. Result ID: 698e41bbffc3901de09c1211.

[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.

### Easy BCQ

Normalized Avg Return: 67. Result ID: 698e85bcffc3901de09e51a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df51.md>)

[Implementation](<https://github.com/davidbrandfonbrener/onestep-rl>)

Recorded evaluation configuration: {"Algorithmic Template":"One-step"}. This record does not assert independent reproduction.

### SAC-N

Normalized Avg Return: 64.1. Result ID: 698e41bbffc3901de09c1210.

[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.

### Fu et al.

Normalized Avg Return: 56.9. Result ID: 698e85bcffc3901de09e51a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa693c1e209131cea210fc.md>)

Recorded evaluation configuration: {"Algorithmic Template":"Iterative"}. This record does not assert independent reproduction.

### Rev. KL Reg.

Normalized Avg Return: 55.3. Result ID: 698e85bcffc3901de09e51a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df51.md>)

[Implementation](<https://github.com/davidbrandfonbrener/onestep-rl>)

Recorded evaluation configuration: {"Algorithmic Template":"One-step"}. This record does not assert independent reproduction.

### Exp. Weight

Normalized Avg Return: 54.7. Result ID: 698e85bcffc3901de09e51a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df51.md>)

[Implementation](<https://github.com/davidbrandfonbrener/onestep-rl>)

Recorded evaluation configuration: {"Algorithmic Template":"One-step"}. This record does not assert independent reproduction.

### BC

Normalized Avg Return: 49.3. Result ID: 698e85bcffc3901de09e51a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df51.md>)

Recorded evaluation configuration: {"Algorithmic Template":"One-step"}. This record does not assert independent reproduction.

### PT+IQL

Normalized Avg Return: 42.9. Result ID: 69918eee3a6c31484908f8fe.

[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.

### CQL

Normalized Avg Return: 40.3. Result ID: 698e41bbffc3901de09c120e.

[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.

### BC

Normalized Avg Return: 38.3. Result ID: 698e41bbffc3901de09c120b.

[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 Avg Return: 37.4. Result ID: 69918eee3a6c31484908f8fb.

[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.

### CQL

Normalized Avg Return: 27.2. Result ID: 698e41bbffc3901de09c120f.

[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 Avg Return: 18.3. Result ID: 69918eee3a6c31484908f8fd.

[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

Normalized Avg Return: -0.8. Result ID: 698e41bbffc3901de09c120c.

[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.

### REM

Normalized Avg Return: -1. Result ID: 698e41bbffc3901de09c120d.

[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.

### PT+RvS

Normalized Avg Return: -2.2. Result ID: 69918eee3a6c31484908f8fc.

[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.
