# Offline Reinforcement Learning on antmaze large-play

Source: [Offline Reinforcement Learning on antmaze large-play](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-antmaze-large-play>)

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

Data updated: 2026-02-26T06:03:44.538Z

Evaluation of Offline Reinforcement Learning performance on the AntMaze large-play environment, reporting the raw 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 | Offline Reinforcement Learning |
| Dataset (including any stated split) | antmaze large-play |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [Score](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-antmaze-large-play.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| GCPC | 78.2 | Not recorded | 68fa71031e209131cea4e876 |
| TAP | 74 | Not recorded | 68fa71031e209131cea4e876 |
| IQL | 50 | Not recorded | 68fa71031e209131cea4e876 |
| GCIQL | 40 | Not recorded | 68fa71031e209131cea4e876 |
| IQL | 39.6 | Not recorded | 68fa6dc11e209131cea3be20 |
| IQL+smoothing | 38.3 | Not recorded | 68fa6dc11e209131cea3be20 |
| CQL | 36.4 | Not recorded | 68fa71031e209131cea4e876 |
| RvS-G | 35.6 | Not recorded | 68fa71031e209131cea4e876 |
| ROMI+BCQ | 20.2 | Not recorded | 68fa6dc11e209131cea3be20 |
| RORL | 16.3 | Not recorded | 68fa6dc11e209131cea3be20 |
| CQL | 15.8 | Not recorded | 68fa6dc11e209131cea3be20 |
| DWSL | 15.2 | Not recorded | 68fa71031e209131cea4e876 |
| WGCSL | 0.6 | Not recorded | 68fa71031e209131cea4e876 |
| TD3+BC | 0.2 | Not recorded | 68fa6dc11e209131cea3be20 |
| BC | 0 | Not recorded | 68fa6dc11e209131cea3be20 |
| AWAC | 0 | Not recorded | 68fa6dc11e209131cea3be20 |
| BC | 0 | Not recorded | 68fa71031e209131cea4e876 |
| DT | 0 | Not recorded | 68fa71031e209131cea4e876 |

### GCPC

Score: 78.2. Result ID: 69916c773a6c314849080dfe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

[Implementation](<https://brown-palm.github.io/GCPC/>)

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

### TAP

Score: 74. Result ID: 69916c773a6c314849080df9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e621e209131cea3f8d7.md>)

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

### IQL

Score: 50. Result ID: 69916c773a6c314849080df7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

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

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

### GCIQL

Score: 40. Result ID: 69916c773a6c314849080dfb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

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

### IQL

Score: 39.6. Result ID: 698fe55d3a6c314849fca289.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be20.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+smoothing

Score: 38.3. Result ID: 698fe55d3a6c314849fca28a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be20.md>)

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

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

### CQL

Score: 36.4. Result ID: 69916c773a6c314849080df6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

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

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

### RvS-G

Score: 35.6. Result ID: 69916c773a6c314849080dfd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

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

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

### ROMI+BCQ

Score: 20.2. Result ID: 698fe55d3a6c314849fca288.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b431e209131cea2d143.md>)

[Implementation](<https://sites.google.com/view/romi-offlinerl/>)

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

### RORL

Score: 16.3. Result ID: 698fe55d3a6c314849fca28b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be20.md>)

[Implementation](<https://github.com/YangRui2015/RORL>)

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

### CQL

Score: 15.8. Result ID: 698fe55d3a6c314849fca287.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be20.md>)

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

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

### DWSL

Score: 15.2. Result ID: 69916c773a6c314849080dfc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea440c5.md>)

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

### WGCSL

Score: 0.6. Result ID: 69916c773a6c314849080dfa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

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

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

### TD3+BC

Score: 0.2. Result ID: 698fe55d3a6c314849fca286.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be20.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.

### BC

Score: 0. Result ID: 698fe55d3a6c314849fca284.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be20.md>)

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

### AWAC

Score: 0. Result ID: 698fe55d3a6c314849fca285.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be20.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

Score: 0. Result ID: 69916c773a6c314849080df5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61c81e209131ce9f5cc2.md>)

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

### DT

Score: 0. Result ID: 69916c773a6c314849080df8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e876.md>)

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