# Offline Reinforcement Learning on D4RL Hopper Medium-Replay

Source: [Offline Reinforcement Learning on D4RL Hopper Medium-Replay](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-hopper-medium-replay>)

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

Data updated: 2026-05-08T08:20:35.741Z

Evaluation of Offline Reinforcement Learning performance on the D4RL Hopper environment using the Medium-Replay dataset configuration, measured by Reward.

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 Hopper Medium-Replay |
| Metric | Reward |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 32 of 32 |
| 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/offline-reinforcement-learning-on-d4rl-hopper-medium-replay.md?metric=Reward>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Reward | Result date | Report paper |
| --- | --- | --- | --- |
| D-QL | 100.7 | Not recorded | 68fa76891e209131cea6d825 |
| RTB | 100.4 | Not recorded | 68fa76891e209131cea6d825 |
| DD | 100 | Not recorded | 68fa76891e209131cea6d825 |
| QGPO | 96.9 | Not recorded | 68fa76891e209131cea6d825 |
| Diffuser | 96.8 | Not recorded | 68fa71061e209131cea4ea5a |
| D | 96.8 | Not recorded | 68fa76891e209131cea6d825 |
| RGG+ | 95.8 | Not recorded | 68fa71061e209131cea4ea5a |
| RGG | 95.2 | Not recorded | 68fa71061e209131cea4ea5a |
| CQL | 95 | Not recorded | 68fa71061e209131cea4ea5a |
| CQL | 95 | Not recorded | 68fa76891e209131cea6d825 |
| IQL | 94.7 | Not recorded | 68fa71061e209131cea4ea5a |
| IQL | 94.7 | Not recorded | 68fa76891e209131cea6d825 |
| MOREL | 93.6 | Not recorded | 68fa71061e209131cea4ea5a |
| IDQL | 92.1 | Not recorded | 68fa76891e209131cea6d825 |
| TT | 91.5 | Not recorded | 68fa71061e209131cea4ea5a |
| IQL | 88.46 | Not recorded | 68fa7b971e209131cea8953c |
| DT | 82.7 | Not recorded | 68fa71061e209131cea4ea5a |
| Transformer | 79.73 | Not recorded | 68fa734f1e209131cea5bba8 |
| DT | 79.7 | Not recorded | 68fa6cbf1e209131cea35c2d |
| Aaren | 77.87 | Not recorded | 68fa734f1e209131cea5bba8 |
| FLOWFORMER | 75.5 | Not recorded | 68fa6cbf1e209131cea35c2d |
| Linear Trans. | 74.3 | Not recorded | 68fa6cbf1e209131cea35c2d |
| FQL+BC | 73.33 | Not recorded | 68fa7b971e209131cea8953c |
| MOPO | 67.5 | Not recorded | 68fa71061e209131cea4ea5a |
| Reformer | 66.1 | Not recorded | 68fa6cbf1e209131cea35c2d |
| Performer | 64.6 | Not recorded | 68fa6cbf1e209131cea35c2d |
| cosFormer | 59.3 | Not recorded | 68fa6cbf1e209131cea35c2d |
| AWAC | 37.2 | Not recorded | 68fa6cbf1e209131cea35c2d |
| BC | 18.1 | Not recorded | 68fa6cbf1e209131cea35c2d |
| BC | 18.1 | Not recorded | 68fa71061e209131cea4ea5a |
| BC | 18.1 | Not recorded | 68fa76891e209131cea6d825 |
| MBOP | 12.4 | Not recorded | 68fa71061e209131cea4ea5a |

### D-QL

Reward: 100.7. Result ID: 69943f7a3a6c3148491c0d28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70791e209131cea4b56e.md>)

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

### RTB

Reward: 100.4. Result ID: 69943f7a3a6c3148491c0d2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

[Implementation](<https://github.com/GFNOrg/diffusion-finetuning>)

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

### DD

Reward: 100. Result ID: 69943f7a3a6c3148491c0d27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ffa1e209131cea4849f.md>)

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

### QGPO

Reward: 96.9. Result ID: 69943f7a3a6c3148491c0d2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f931e209131cea465bc.md>)

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

### Diffuser

Reward: 96.8. Result ID: 69916f333a6c3148490823c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e868.md>)

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

### D

Reward: 96.8. Result ID: 69943f7a3a6c3148491c0d26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e868.md>)

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

### RGG+

Reward: 95.8. Result ID: 69916f333a6c3148490823c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Implementation](<https://github.com/leekwoon/rgg>)

Recorded evaluation configuration: {"planning seeds":15}. This record does not assert independent reproduction.

### RGG

Reward: 95.2. Result ID: 69916f333a6c3148490823c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Implementation](<https://github.com/leekwoon/rgg>)

Recorded evaluation configuration: {"planning seeds":15}. This record does not assert independent reproduction.

### CQL

Reward: 95. Result ID: 69916f333a6c3148490823b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

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

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

### CQL

Reward: 95. Result ID: 69943f7a3a6c3148491c0d24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

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

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

### IQL

Reward: 94.7. Result ID: 69916f333a6c3148490823ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b67f.md>)

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

### IQL

Reward: 94.7. Result ID: 69943f7a3a6c3148491c0d25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b67f.md>)

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

### MOREL

Reward: 93.6. Result ID: 69916f333a6c3148490823be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

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

### IDQL

Reward: 92.1. Result ID: 69943f7a3a6c3148491c0d29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f731e209131cea45a93.md>)

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

### TT

Reward: 91.5. Result ID: 69916f333a6c3148490823bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b511e209131cea2d9cb.md>)

[Implementation](<https://www.sota2.com/github.com/jannerm/trajectory-transformer>)

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

### IQL

Reward: 88.46. Result ID: 69fd9cc647f34ce924e08ac7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b971e209131cea8953c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b67f.md>)

Recorded evaluation configuration: {"Training timesteps":"1M","Random seeds":"10"}. This record does not assert independent reproduction.

### DT

Reward: 82.7. Result ID: 69916f333a6c3148490823bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

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

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

### Transformer

Reward: 79.73. Result ID: 6992b99e3a6c314849110921.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734f1e209131cea5bba8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713e1e209131cea50092.md>)

[Implementation](<https://github.com/thuml/Nonstationary_Transformers>)

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

### DT

Reward: 79.7. Result ID: 698f3a813a6c314849f73843.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c2d.md>)

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

Recorded evaluation configuration: {"Layers":3,"Hidden Channels":256,"Heads":4}. This record does not assert independent reproduction.

### Aaren

Reward: 77.87. Result ID: 6992b99e3a6c314849110922.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734f1e209131cea5bba8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734f1e209131cea5bba8.md>)

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

### FLOWFORMER

Reward: 75.5. Result ID: 698f3a813a6c314849f73848.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c2d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c2d.md>)

[Implementation](<https://github.com/thuml/Flowformer>)

Recorded evaluation configuration: {"Layers":3,"Hidden Channels":256,"Heads":4}. This record does not assert independent reproduction.

### Linear Trans.

Reward: 74.3. Result ID: 698f3a813a6c314849f73844.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c2d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68471e209131cea1b069.md>)

[Implementation](<https://linear-transformers.com/>)

Recorded evaluation configuration: {"Layers":3,"Hidden Channels":256,"Heads":4}. This record does not assert independent reproduction.

### FQL+BC

Reward: 73.33. Result ID: 69fd9cc647f34ce924e08ac6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b971e209131cea8953c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b971e209131cea8953c.md>)

Recorded evaluation configuration: {"Training timesteps":"1M","Random seeds":"10"}. This record does not assert independent reproduction.

### MOPO

Reward: 67.5. Result ID: 69916f333a6c3148490823bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c11e209131cea1e111.md>)

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

### Reformer

Reward: 66.1. Result ID: 698f3a813a6c314849f73845.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c2d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671b1e209131cea143ed.md>)

[Implementation](<https://github.com/google/trax/tree/master/trax/models/reformer>)

Recorded evaluation configuration: {"Layers":3,"Hidden Channels":256,"Heads":4}. This record does not assert independent reproduction.

### Performer

Reward: 64.6. Result ID: 698f3a813a6c314849f73846.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c2d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d699.md>)

[Implementation](<https://github.com/google-research/google-research/tree/master/performer>)

Recorded evaluation configuration: {"Layers":3,"Hidden Channels":256,"Heads":4}. This record does not assert independent reproduction.

### cosFormer

Reward: 59.3. Result ID: 698f3a813a6c314849f73847.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c2d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd21e209131cea304be.md>)

[Implementation](<https://www.sota2.com/cosFormer>)

Recorded evaluation configuration: {"Layers":3,"Hidden Channels":256,"Heads":4}. This record does not assert independent reproduction.

### AWAC

Reward: 37.2. Result ID: 698f3a813a6c314849f73842.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c2d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea24226.md>)

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

### BC

Reward: 18.1. Result ID: 698f3a813a6c314849f73841.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c2d.md>)

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

### BC

Reward: 18.1. Result ID: 69916f333a6c3148490823b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

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

### BC

Reward: 18.1. Result ID: 69943f7a3a6c3148491c0d23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d825.md>)

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

### MBOP

Reward: 12.4. Result ID: 69916f333a6c3148490823bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71061e209131cea4ea5a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69931e209131cea22c5e.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.
