PKU-Alignment / Safe-Policy-Optimization

NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms
https://safe-policy-optimization.readthedocs.io/en/latest/index.html
Apache License 2.0
330 stars 45 forks source link

Safexp-PointGoal1-v0 vs SafetyPointGoal1-v0 #21

Closed YUYING07 closed 1 year ago

YUYING07 commented 1 year ago

Dear,

what is the difference between Safexp-PointGoal1-v0 vs SafetyPointGoal1-v0?

I find that, result from SafetyPointGoal1-v0 is generally smaller than Safexp-PointGoal1-v0

muchvo commented 1 year ago

We update the MuJoCo version, from 2.0.0 to 2.3.0, so there may be some difference in the underlying physical mechanism. In short, You can consider the setting of the two tasks is completely the same, while SafetyPointGoal1-v0 is easier to use. For other environments, it goes the same.

muchvo commented 1 year ago

For more information, You can refer to the official page: https://github.com/PKU-MARL/Safety-Gymnasium