Winning at Pokémon Random Battles Using Reinforcement Learning
Name
wang-jett-meng-eecs-2024-thesis.pdf
Description
Thesis PDF
Size
1.3 MB
Format
Adobe PDF
Checksum (MD5)
b9b73e45eb45bddad400ae207ce8720e
Author(s)
Wang, Jett
Advisor(s)
Tenenbaum, Joshua
Date Issued
February 2024
Publisher
Massachusetts Institute of Technology
Abstract
Pokémon battling is a challenging domain for reinforcement learning techniques, due to the massive state space, stochasticity, and partial observability. We demonstrate an agent which employs a Monte Carlo Tree Search informed by a actor-critic network trained using Proximal Policy Optimization with experience collected through self-play. The agent peaked at rank 8 (1693 Elo) on the official Pokémon Showdown gen4randombattles ladder, which is the best known performance by any non-human agent for this format. This strong showing lays the foundation for superhuman performance in Pokémon and other complex turn-based games of imperfect information, expanding the viability of methods which have historically been used in perfect-information games.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
