How can I use the SAC algorithm (instead of the default PPO) to train Ant?

[chenci107]

https://github.com/NVIDIA-Omniverse/IsaacGymEnvs/blob/main/docs/rl_examples.md
The above website says that Ant tasks can be trained using the SAC algorithm, but there is no specific modification of the configuration to AntSAC.yaml. What should I do? Thanks :）

[Skylark0924]

https://github.com/NVIDIA-Omniverse/IsaacGymEnvs/blob/main/docs/rl_examples.md The above website says that Ant tasks can be trained using the SAC algorithm, but there is no specific modification of the configuration to AntSAC.yaml. What should I do? Thanks :）

You can check my package Rofunc.
https://github.com/Skylark0924/Rofunc/tree/main
Here is an example of AntSAC:
https://github.com/Skylark0924/Rofunc/blob/main/examples/learning_rl/IsaacGym_RofuncRL/example_Ant_RofuncRL.py