rishihahs / pokemonai Public

Notifications You must be signed in to change notification settings
Fork 5
Star 17

Reinforcement learning approach to playing competitive Pokémon.

17 stars 5 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
pokemonai		pokemonai
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
requirements.txt		requirements.txt
setup.py		setup.py

Repository files navigation

Pokémon AI

Goal

Reinforcement learning approach to playing competitive Pokémon. Battling is done on Smogon's Pokémon Showdown! battle simulator.

Ideas to Explore

Batch RL (experience replay/fitted Q iteration)
Online TD Learning
PG methods (DDPG)
Monte Carlo Tree Search (with simplfied assumptions)
Imitation learning with Smogon leaderboard

About

Reinforcement learning approach to playing competitive Pokémon.

pokemon reinforcement-learning pokemon-showdown

Report repository

Releases

No releases published

Packages

Languages

Python 100.0%