Open dota2heqiuzhi opened 1 year ago
stable-retro (and gym-retro) is based off of retroArch. So this is not possible without significant changes to the codebase
Isn't he asking about using a retroarch core (mame2003-plus-libretro)?
That would be awesome!
That said there is no official guide yet but you can check this to get started: New Emulator Integration Tutorial
You can join stable-retro discord channel if you need help: https://discord.gg/dXuBSg3B4D
stable-retro (and gym-retro) is based off of retroArch. So this is not possible without significant changes to the codebase
I see that Gym Retro supports the Libretro API, and MAME 2003-Plus is also developed based on Libretro. So there may not be much that needs to be changed, right?
That would be awesome!
That said there is no official guide yet but you can check this to get started: New Emulator Integration Tutorial
You can join stable-retro discord channel if you need help: https://discord.gg/dXuBSg3B4D
I have seen his post, and he hasn't updated it since his failed attempt. After I put the MAME core in, do I need to compile the code myself?
According to his steps, seems yes you need to recompile. I will try myself later this month and make a video tutorial if I succeed
According to his steps, seems yes you need to recompile. I will try myself later this month and make a video tutorial if I succeed
Can you test it using the double dragon Neo-Geo? You can download the ROM from here: https://archive.org/details/MAME_2003-Plus_Reference_Set_2018. The lib is available at https://github.com/libretro/mame2003-plus-libretro.
@dota2heqiuzhi I will check it out
@dota2heqiuzhi stable-retro has moved to Farama fondation: https://github.com/Farama-Foundation/stable-retro
Can you recreate your issue there so that it's under your user name? I will continue to follow over there
@dota2heqiuzhi stable-retro has moved to Farama fondation: https://github.com/Farama-Foundation/stable-retro
Can you recreate your issue there so that it's under your user name? I will continue to follow over there
Okay, thank you very much! I'll rely on you for my introduction to reinforcement learning.
I want to integrate mame2003-plus-libretro emulator in stable-retro. So I can train an AI on the game Double Dragon (there are many versions of this game, but I'm looking for the 1995 fighting game released on Neo-Geo and PS1).
Can someone provide some tutorials or give step-by-step instructions? For example, do I need to modify the source code myself, or compile the source code? Thank you very much! I am a beginner and really don't know what to do. I really want to use this game to train an AI and get started with reinforcement learning.