Work published in 23rd Brazilian Symposium on Games and Digital Entertainment (SBGames-2024). This paper presents an open-source benchmark of trained agents with classic RL methods and Deep Reinforcement Learning (DRL) techniques - PokeRL repository.
I Choose You, Reinforcement Learning! Trained RL Agents For Pokémon Battles / 2024 / 23rd Brazilian Symposium on Games and Digital Entertainment (SBGames-2024)
Pokémon battles present a valuable training environment for Reinforcement Learning (RL) agents due to their inherent stochastic nature and adaptability to deterministic settings. However, this environment currently lacks a comprehensive benchmark of basic RL agent implementations suitable for training purposes. This project aims to fill this gap with an open-source benchmark of trained agents with classic RL methods and Deep Reinforcement Learning (DRL) techniques, to foster the development in the field and facilitate the entry of new researchers. We also propose a Markov Decision Process (MDP) environment, in which agents are trained and validated. The agents demonstrated effective learning and achieved robust performance during training.
ROSSI, Leonardo de Lellis; SOUZA, Bruno; LOPES, Maurício Pereira; GUDWIN, Ricardo Ribeiro; COLOMBINI, Esther Luna. I Choose You, Reinforcement Learning! Trained RL Agents For Pokémon Battles. In: COMPUTING TRACK – SHORT PAPERS - BRAZILIAN SYMPOSIUM ON COMPUTER GAMES AND DIGITAL ENTERTAINMENT (SBGAMES) , 2024. Porto Alegre: Sociedade Brasileira de Computação, 2024 . p. 13-18. DOI: https://doi.org/10.5753/sbgames_estendido.2024.241242.