# Goal1 on Safety Gymnasium

Source: [Goal1 on Safety Gymnasium](<https://www.sota2.com/research/sota/goal1-on-safety-gymnasium>)

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

Data updated: 2026-02-26T06:02:18.331Z

Evaluation of performance on the Goal1 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 | Goal1 |
| Dataset (including any stated split) | Safety Gymnasium |
| Metric | Reward |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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/goal1-on-safety-gymnasium.md?metric=Reward>): Higher is better; unit: SCALAR.

- [Cost](<https://www.sota2.com/research/sota/goal1-on-safety-gymnasium.md?metric=Cost>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Reward | Result date | Report paper |
| --- | --- | --- | --- |
| DDPG | 7.9 | Not recorded | 68fa7c6b1e209131cea8df7e |
| SC | 7.57 | Not recorded | 68fa7c6b1e209131cea8df7e |
| CSC | 7.21 | Not recorded | 68fa7c6b1e209131cea8df7e |
| USC | 7.19 | Not recorded | 68fa7c6b1e209131cea8df7e |
| CPO | 6.76 | Not recorded | 68fa7c6b1e209131cea8df7e |
| RCPO | 6.74 | Not recorded | 68fa7c6b1e209131cea8df7e |
| SC | 6.6 | Not recorded | 68fa7c6b1e209131cea8df7e |
| DDPG | 6.57 | Not recorded | 68fa7c6b1e209131cea8df7e |
| RCPO | 6.56 | Not recorded | 68fa7c6b1e209131cea8df7e |
| CSC | 6.56 | Not recorded | 68fa7c6b1e209131cea8df7e |
| USC (NR) | 6.56 | Not recorded | 68fa7c6b1e209131cea8df7e |
| USC | 6.55 | Not recorded | 68fa7c6b1e209131cea8df7e |
| PID-Lag | 6.5 | Not recorded | 68fa7c6b1e209131cea8df7e |
| PID-Lag | 6.48 | Not recorded | 68fa7c6b1e209131cea8df7e |
| CPO | 6.4 | Not recorded | 68fa7c6b1e209131cea8df7e |
| USC (NR) | 5.79 | Not recorded | 68fa7c6b1e209131cea8df7e |

### DDPG

Reward: 7.9. Result ID: 699af4305698665ec4857ba3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fd1e209131cea0dc8e.md>)

Recorded evaluation configuration: {"chi":"1.0"}. This record does not assert independent reproduction.

### SC

Reward: 7.57. Result ID: 699af4305698665ec4857ba7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa689d1e209131cea1d196.md>)

Recorded evaluation configuration: {"chi":"1.0"}. This record does not assert independent reproduction.

### CSC

Reward: 7.21. Result ID: 699af4305698665ec4857ba8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea2424d.md>)

Recorded evaluation configuration: {"chi":"1.0"}. This record does not assert independent reproduction.

### USC

Reward: 7.19. Result ID: 699af4305698665ec4857baa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

Recorded evaluation configuration: {"chi":"1.0","Refinement":"Refined"}. This record does not assert independent reproduction.

### CPO

Reward: 6.76. Result ID: 699af4305698665ec4857ba5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63691e209131ce9fe8ff.md>)

Recorded evaluation configuration: {"chi":"1.0"}. This record does not assert independent reproduction.

### RCPO

Reward: 6.74. Result ID: 699af4305698665ec4857ba6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65321e209131cea08cff.md>)

Recorded evaluation configuration: {"chi":"1.0"}. This record does not assert independent reproduction.

### SC

Reward: 6.6. Result ID: 699af4305698665ec4857bff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa689d1e209131cea1d196.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"1.0"}. This record does not assert independent reproduction.

### DDPG

Reward: 6.57. Result ID: 699af4305698665ec4857bfb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fd1e209131cea0dc8e.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"1.0"}. This record does not assert independent reproduction.

### RCPO

Reward: 6.56. Result ID: 699af4305698665ec4857bfe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65321e209131cea08cff.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"1.0"}. This record does not assert independent reproduction.

### CSC

Reward: 6.56. Result ID: 699af4305698665ec4857c00.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea2424d.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"1.0"}. This record does not assert independent reproduction.

### USC (NR)

Reward: 6.56. Result ID: 699af4305698665ec4857c01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"1.0"}. This record does not assert independent reproduction.

### USC

Reward: 6.55. Result ID: 699af4305698665ec4857c02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"1.0"}. This record does not assert independent reproduction.

### PID-Lag

Reward: 6.5. Result ID: 699af4305698665ec4857ba4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa571c1e209131ce9a29c4.md>)

Recorded evaluation configuration: {"chi":"1.0"}. This record does not assert independent reproduction.

### PID-Lag

Reward: 6.48. Result ID: 699af4305698665ec4857bfc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa571c1e209131ce9a29c4.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"1.0"}. This record does not assert independent reproduction.

### CPO

Reward: 6.4. Result ID: 699af4305698665ec4857bfd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63691e209131ce9fe8ff.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"1.0"}. This record does not assert independent reproduction.

### USC (NR)

Reward: 5.79. Result ID: 699af4305698665ec4857ba9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

Recorded evaluation configuration: {"chi":"1.0","Refinement":"None"}. This record does not assert independent reproduction.

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