Open TaoshuaiZ opened 6 months ago
Hi, sorry about the late reply -- you can take a look at the notebook at https://www.dropbox.com/scl/fi/urv0mb9pvsrd83gfsf9c5/sim_mcts.ipynb?rlkey=inpwd8pvptzzvma4o9m4i1i2k&dl=0
Unfortunately the notebook is not directly runnable, but hopefully the line_reward_function, pairwise_reward_function and region_reward_function are helpful.
Thank you! The notebook is helpful!
I'm recently doing some research following VLP. And there are many details that I want to figure out, such as how to define the success of the tasks in VLP. Could you please release the code and I will appreciate it.