# CarGoal1 on Safety Gymnasium

Source: [CarGoal1 on Safety Gymnasium](<https://www.sota2.com/research/sota/cargoal1-on-safety-gymnasium>)

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

Data updated: 2026-04-30T07:42:40.924Z

Evaluation of agent performance on the CarGoal1 task within the Safety Gymnasium environment, focusing on Reward and Cost metrics.

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 | CarGoal1 |
| Dataset (including any stated split) | Safety Gymnasium |
| Metric | Reward |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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/cargoal1-on-safety-gymnasium.md?metric=Reward>): Higher is better; unit: PERCENT.

- [Cost](<https://www.sota2.com/research/sota/cargoal1-on-safety-gymnasium.md?metric=Cost>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Reward | Result date | Report paper |
| --- | --- | --- | --- |
| CPQ | 79 | Not recorded | 69f2e23455a3c32af89fc7ec |
| CPQ | 79 | Not recorded | 69f2e23455a3c32af89fc7ec |
| DT + SAS | 67 | Not recorded | 69f2e23455a3c32af89fc7ec |
| DT + SAS | 67 | Not recorded | 69f2e23455a3c32af89fc7ec |
| CDT | 66 | Not recorded | 69f2e23455a3c32af89fc7ec |
| CDT | 66 | Not recorded | 69f2e23455a3c32af89fc7ec |
| CDT + SAS | 65 | Not recorded | 69f2e23455a3c32af89fc7ec |
| CDT + SAS | 65 | Not recorded | 69f2e23455a3c32af89fc7ec |
| BEAR-Lag | 61 | Not recorded | 69f2e23455a3c32af89fc7ec |
| BEAR-Lag | 61 | Not recorded | 69f2e23455a3c32af89fc7ec |
| BCQ-Lag | 47 | Not recorded | 69f2e23455a3c32af89fc7ec |
| BCQ-Lag | 47 | Not recorded | 69f2e23455a3c32af89fc7ec |
| BC-All | 39 | Not recorded | 69f2e23455a3c32af89fc7ec |
| BC-All | 39 | Not recorded | 69f2e23455a3c32af89fc7ec |
| COptiDICE | 35 | Not recorded | 69f2e23455a3c32af89fc7ec |
| DCRL | 35 | Not recorded | 69f2e23455a3c32af89fc7ec |
| COptiDICE | 35 | Not recorded | 69f2e23455a3c32af89fc7ec |
| BC-Safe | 24 | Not recorded | 69f2e23455a3c32af89fc7ec |
| BC-Safe | 24 | Not recorded | 69f2e23455a3c32af89fc7ec |

### CPQ

Reward: 79. Result ID: 69f3071147f34ce924d92374.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c381e209131cea32de5.md>)

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

### CPQ

Reward: 79. Result ID: 69f3071147f34ce924d92402.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c381e209131cea32de5.md>)

Recorded evaluation configuration: {"cost thresholds":"3","evaluation episodes":"20","random seeds":"3"}. This record does not assert independent reproduction.

### DT + SAS

Reward: 67. Result ID: 69f3071147f34ce924d9236d.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

Recorded evaluation configuration: {"Backbone":"DT","Alignment strategy (SAS)":"Lyapunov-Guided"}. This record does not assert independent reproduction.

### DT + SAS

Reward: 67. Result ID: 69f3071147f34ce924d923fb.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

Recorded evaluation configuration: {"cost thresholds":"3","evaluation episodes":"20","random seeds":"3"}. This record does not assert independent reproduction.

### CDT

Reward: 66. Result ID: 69f3071147f34ce924d9236f.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc61e209131cea47551.md>)

Recorded evaluation configuration: {"Backbone":"CDT"}. This record does not assert independent reproduction.

### CDT

Reward: 66. Result ID: 69f3071147f34ce924d923fd.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc61e209131cea47551.md>)

Recorded evaluation configuration: {"cost thresholds":"3","evaluation episodes":"20","random seeds":"3"}. This record does not assert independent reproduction.

### CDT + SAS

Reward: 65. Result ID: 69f3071147f34ce924d9236e.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

Recorded evaluation configuration: {"Backbone":"CDT","Alignment strategy (SAS)":"Lyapunov-Guided"}. This record does not assert independent reproduction.

### CDT + SAS

Reward: 65. Result ID: 69f3071147f34ce924d923fc.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

Recorded evaluation configuration: {"cost thresholds":"3","evaluation episodes":"20","random seeds":"3"}. This record does not assert independent reproduction.

### BEAR-Lag

Reward: 61. Result ID: 69f3071147f34ce924d92373.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c381e209131cea32de5.md>)

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

### BEAR-Lag

Reward: 61. Result ID: 69f3071147f34ce924d92401.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c381e209131cea32de5.md>)

Recorded evaluation configuration: {"cost thresholds":"3","evaluation episodes":"20","random seeds":"3"}. This record does not assert independent reproduction.

### BCQ-Lag

Reward: 47. Result ID: 69f3071147f34ce924d92372.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c381e209131cea32de5.md>)

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

### BCQ-Lag

Reward: 47. Result ID: 69f3071147f34ce924d92400.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c381e209131cea32de5.md>)

Recorded evaluation configuration: {"cost thresholds":"3","evaluation episodes":"20","random seeds":"3"}. This record does not assert independent reproduction.

### BC-All

Reward: 39. Result ID: 69f3071147f34ce924d92370.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc61e209131cea47551.md>)

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

### BC-All

Reward: 39. Result ID: 69f3071147f34ce924d923fe.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc61e209131cea47551.md>)

Recorded evaluation configuration: {"cost thresholds":"3","evaluation episodes":"20","random seeds":"3"}. This record does not assert independent reproduction.

### COptiDICE

Reward: 35. Result ID: 69f3071147f34ce924d92375.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c511e209131cea333c4.md>)

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

### DCRL

Reward: 35. Result ID: 69f3071147f34ce924d92376.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a391e209131cea26b7e.md>)

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

### COptiDICE

Reward: 35. Result ID: 69f3071147f34ce924d92403.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c511e209131cea333c4.md>)

Recorded evaluation configuration: {"cost thresholds":"3","evaluation episodes":"20","random seeds":"3"}. This record does not assert independent reproduction.

### BC-Safe

Reward: 24. Result ID: 69f3071147f34ce924d92371.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc61e209131cea47551.md>)

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

### BC-Safe

Reward: 24. Result ID: 69f3071147f34ce924d923ff.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e23455a3c32af89fc7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc61e209131cea47551.md>)

Recorded evaluation configuration: {"cost thresholds":"3","evaluation episodes":"20","random seeds":"3"}. This record does not assert independent reproduction.

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