Skip to content

Test ground for reinforcement learning using pokemon showdown.

Notifications You must be signed in to change notification settings

Patrick-Hogeveen/PokemonAI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PokemonAI

Test ground for reinforcement learning using pokemon showdown.

Start:

clone the pokemonshowdown repo here: https://github.com/smogon/pokemon-showdown
run node ./pokemon-showdown/pokemon-showdown start --no-security in root to start the server run python scripts at your leisure

-Random and MaxDamage scripts written from poke env examples -playerml is a combination of examples and pytorch dqn algorithm

TODO:

-playerml needs better logging of stats ie. amount of dmg taken, number of super effective moves used, etc. Just items to see how well the AI is doing

About

Test ground for reinforcement learning using pokemon showdown.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages