Human-Level Competitive Pokémon via Scalable Offline Reinforcement Learning with Transformers
Paper • 2504.04395 • Published
Metamon training checkpoints for policies that play Pokémon Showdown at a human level.
Paper: Human-Level Competitive Pokémon via Scalable Offline Reinforcement Learning with Transformers
Project Website: https://metamon.tech
Code: GitHub Repository
The metamon README provides detailed instructions for loading, evaluating, and finetuning pretrained policies.