Hello, I noticed that in your paper there is a section named "Goal-directed generative capabilities", which uses reinforcement learning to optimize the generation capability for specified properties. However, I couldn't find related instructions in this repo or in the docs. It will be really helpful if you can share the code or tutorial. Thank you in advance!
Hello, I noticed that in your paper there is a section named "Goal-directed generative capabilities", which uses reinforcement learning to optimize the generation capability for specified properties. However, I couldn't find related instructions in this repo or in the docs. It will be really helpful if you can share the code or tutorial. Thank you in advance!