Hello everyone, I've been working on a project to use reinforcement learning to learn PvP in Old School RuneScape for the past year. I've finally reached a point where I'm satisfied with the result, so I've open sourced (most of) the project, and released a youtube video going over how it works from a high level.
* GitHub: GitHub - Naton1/osrs-pvp-reinforcement-learning: Train a neural network to PvP in Old School RuneScape using reinforcement learning.
* Youtube:
Note that nothing is open sourced to run the models on the real game so as to not impact it, but everything else is available (training simulation, reinforcement learning code). There's no bots or scripts available here, so please don't ask about it.
* GitHub: GitHub - Naton1/osrs-pvp-reinforcement-learning: Train a neural network to PvP in Old School RuneScape using reinforcement learning.
* Youtube:
Note that nothing is open sourced to run the models on the real game so as to not impact it, but everything else is available (training simulation, reinforcement learning code). There's no bots or scripts available here, so please don't ask about it.
