# Locomotion on D4RL MuJoCo Tasks (Average across v2 Environments)

Source: [Locomotion on D4RL MuJoCo Tasks (Average across v2 Environments)](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments>)

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

Data updated: 2026-05-15T09:19:35.846Z

Evaluation of agent performance across the primary D4RL MuJoCo Locomotion tasks (Walker2d, Hopper, HalfCheetah) using Medium, Medium-Expert, and Medium-Replay configurations from version 2, typically reported as an average score.

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 | Locomotion |
| Dataset (including any stated split) | D4RL MuJoCo Tasks |
| Metric | Average D4RL Locomotion Score (v2) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 29 of 29 |
| 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

- [Average D4RL Locomotion Score (v2)](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=Average%20D4RL%20Locomotion%20Score%20(v2)>): Higher is better; unit: SCALAR.

- [Walker2d Medium Expert v2 Score](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=Walker2d%20Medium%20Expert%20v2%20Score>): Higher is better; unit: SCALAR.

- [Walker2d Medium v2 Score](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=Walker2d%20Medium%20v2%20Score>): Higher is better; unit: SCALAR.

- [Walker2d Medium Replay v2 Score](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=Walker2d%20Medium%20Replay%20v2%20Score>): Higher is better; unit: SCALAR.

- [Hopper Medium Expert v2 Score](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=Hopper%20Medium%20Expert%20v2%20Score>): Higher is better; unit: SCALAR.

- [Hopper Medium v2 Score](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=Hopper%20Medium%20v2%20Score>): Higher is better; unit: SCALAR.

- [Hopper Medium Replay v2 Score](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=Hopper%20Medium%20Replay%20v2%20Score>): Higher is better; unit: SCALAR.

- [HalfCheetah Medium Expert v2 Score](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=HalfCheetah%20Medium%20Expert%20v2%20Score>): Higher is better; unit: SCALAR.

- [HalfCheetah Medium v2 Score](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=HalfCheetah%20Medium%20v2%20Score>): Higher is better; unit: SCALAR.

- [HalfCheetah Medium Replay v2 Score](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=HalfCheetah%20Medium%20Replay%20v2%20Score>): Higher is better; unit: SCALAR.

- [Performance Gain (%)](<https://www.sota2.com/research/sota/locomotion-on-d4rl-mujoco-tasks-average-across-v2-environments.md?metric=Performance%20Gain%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average D4RL Locomotion Score (v2) | Result date | Report paper |
| --- | --- | --- | --- |
| CPQL | 1252.1 | Not recorded | 6a06a8b8dbc836b87d82a1fe |
| EPQ | 1193.7 | Not recorded | 6a06a8b8dbc836b87d82a1fe |
| MCQ | 1188.4 | Not recorded | 6a06a8b8dbc836b87d82a1fe |
| CSVE | 1121.4 | Not recorded | 6a06a8b8dbc836b87d82a1fe |
| MISA | 1081.4 | Not recorded | 6a06a8b8dbc836b87d82a1fe |
| IQL | 1033.1 | Not recorded | 6a06a8b8dbc836b87d82a1fe |
| TD3+BC | 1013.2 | Not recorded | 6a06a8b8dbc836b87d82a1fe |
| CQL | 1010.2 | Not recorded | 6a06a8b8dbc836b87d82a1fe |
| BC | 744.1 | Not recorded | 6a06a8b8dbc836b87d82a1fe |
| PrefMoE | 84.3 | Not recorded | 69f82815c0f56ed843088ab1 |
| DHi | 83.3 | Not recorded | 69fd6e155497b3b670c89419 |
| SlimDT | 82.6 | Not recorded | 69fd6e155497b3b670c89419 |
| DC | 82.2 | Not recorded | 69fd6e155497b3b670c89419 |
| ICQL | 80.6 | Not recorded | 68fa7bb51e209131cea8a0fb |
| CQL | 80.6 | Not recorded | 69fd6e155497b3b670c89419 |
| GDT | 79.1 | Not recorded | 69fd6e155497b3b670c89419 |
| PrefMMT | 77.4 | Not recorded | 69f82815c0f56ed843088ab1 |
| IQL | 77 | Not recorded | 69fd6e155497b3b670c89419 |
| DT | 76.2 | Not recorded | 69fd6e155497b3b670c89419 |
| CQL | 74 | Not recorded | 68fa7bb51e209131cea8a0fb |
| IQL | 72.4 | Not recorded | 68fa7bb51e209131cea8a0fb |
| RIME-offline | 67.3 | Not recorded | 69f82815c0f56ed843088ab1 |
| StAR | 66.2 | Not recorded | 69fd6e155497b3b670c89419 |
| TD3+BC | 62.9 | Not recorded | 68fa7bb51e209131cea8a0fb |
| MR | 60.7 | Not recorded | 69f82815c0f56ed843088ab1 |
| DT | 58.8 | Not recorded | 68fa7bb51e209131cea8a0fb |
| BCQ | 53.8 | Not recorded | 69fd6e155497b3b670c89419 |
| BC | 52.6 | Not recorded | 69fd6e155497b3b670c89419 |
| BC | 51.9 | Not recorded | 68fa7bb51e209131cea8a0fb |

### CPQL

Average D4RL Locomotion Score (v2): 1252.1. Result ID: 6a06e51647f34ce924eed523.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

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

### EPQ

Average D4RL Locomotion Score (v2): 1193.7. Result ID: 6a06e51647f34ce924eed522.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa755b1e209131cea67736.md>)

Recorded evaluation configuration: {"reproduced":"true"}. This record does not assert independent reproduction.

### MCQ

Average D4RL Locomotion Score (v2): 1188.4. Result ID: 6a06e51647f34ce924eed51f.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

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

### CSVE

Average D4RL Locomotion Score (v2): 1121.4. Result ID: 6a06e51647f34ce924eed521.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea50913.md>)

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

### MISA

Average D4RL Locomotion Score (v2): 1081.4. Result ID: 6a06e51647f34ce924eed520.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72531e209131cea55a4a.md>)

[Implementation](<https://github.com/sail-sg/MISA>)

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

### IQL

Average D4RL Locomotion Score (v2): 1033.1. Result ID: 6a06e51647f34ce924eed51e.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

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

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

### TD3+BC

Average D4RL Locomotion Score (v2): 1013.2. Result ID: 6a06e51647f34ce924eed51c.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df4f.md>)

[Implementation](<https://github.com/sfujim/TD3_BC>)

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

### CQL

Average D4RL Locomotion Score (v2): 1010.2. Result ID: 6a06e51647f34ce924eed51d.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

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

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

### BC

Average D4RL Locomotion Score (v2): 744.1. Result ID: 6a06e51647f34ce924eed51b.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b8dbc836b87d82a1fe.md>)

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

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

Recorded evaluation configuration: {"reproduced":"true"}. This record does not assert independent reproduction.

### PrefMoE

Average D4RL Locomotion Score (v2): 84.3. Result ID: 69f85da947f34ce924dc2fe0.

[Reporting paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

Recorded evaluation configuration: {"K":"4"}. This record does not assert independent reproduction.

### DHi

Average D4RL Locomotion Score (v2): 83.3. Result ID: 69fdb46c47f34ce924e127bf.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

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

### SlimDT

Average D4RL Locomotion Score (v2): 82.6. Result ID: 69fdb46c47f34ce924e127c0.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

Recorded evaluation configuration: {"condition injector":"adaLN","variant":"post-cond"}. This record does not assert independent reproduction.

### DC

Average D4RL Locomotion Score (v2): 82.2. Result ID: 69fdb46c47f34ce924e127be.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736b1e209131cea5c645.md>)

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

### ICQL

Average D4RL Locomotion Score (v2): 80.6. Result ID: 69bbb90947f34ce924a5afbf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb51e209131cea8a0fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb51e209131cea8a0fb.md>)

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

### CQL

Average D4RL Locomotion Score (v2): 80.6. Result ID: 69fdb46c47f34ce924e127b7.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

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

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

### GDT

Average D4RL Locomotion Score (v2): 79.1. Result ID: 69fdb46c47f34ce924e127bd.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bb61e209131cea2fca1.md>)

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

### PrefMMT

Average D4RL Locomotion Score (v2): 77.4. Result ID: 69f85da947f34ce924dc2fdf.

[Reporting paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77581e209131cea728d5.md>)

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

### IQL

Average D4RL Locomotion Score (v2): 77. Result ID: 69fdb46c47f34ce924e127b8.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

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

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

### DT

Average D4RL Locomotion Score (v2): 76.2. Result ID: 69fdb46c47f34ce924e127bb.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

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

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

### CQL

Average D4RL Locomotion Score (v2): 74. Result ID: 69bbb90947f34ce924a5afbd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb51e209131cea8a0fb.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

Average D4RL Locomotion Score (v2): 72.4. Result ID: 69bbb90947f34ce924a5afbe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb51e209131cea8a0fb.md>)

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

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

### RIME-offline

Average D4RL Locomotion Score (v2): 67.3. Result ID: 69f85da947f34ce924dc2fde.

[Reporting paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756e1e209131cea67da3.md>)

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

### StAR

Average D4RL Locomotion Score (v2): 66.2. Result ID: 69fdb46c47f34ce924e127bc.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3eef5.md>)

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

### TD3+BC

Average D4RL Locomotion Score (v2): 62.9. Result ID: 69bbb90947f34ce924a5afbc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb51e209131cea8a0fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df4f.md>)

[Implementation](<https://github.com/sfujim/TD3_BC>)

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

### MR

Average D4RL Locomotion Score (v2): 60.7. Result ID: 69f85da947f34ce924dc2fdd.

[Reporting paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26067.md>)

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

### DT

Average D4RL Locomotion Score (v2): 58.8. Result ID: 69bbb90947f34ce924a5afbb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb51e209131cea8a0fb.md>)

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

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

### BCQ

Average D4RL Locomotion Score (v2): 53.8. Result ID: 69fdb46c47f34ce924e127b9.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef4a.md>)

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

### BC

Average D4RL Locomotion Score (v2): 52.6. Result ID: 69fdb46c47f34ce924e127ba.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c89419.md>)

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

### BC

Average D4RL Locomotion Score (v2): 51.9. Result ID: 69bbb90947f34ce924a5afba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb51e209131cea8a0fb.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.
