hsahovic/poke-env
A python interface for training Reinforcement Learning bots to battle on pokemon showdown
Provides battle state abstraction and move legality validation against Pokemon Showdown's game rules, enabling agents to interact via a `Player` subclass interface. Supports async self-play workflows with configurable concurrent battles and integrates with local or remote Showdown servers. Built on asyncio for scalable multi-agent training scenarios.
452 stars and 9,109 monthly downloads. Available on PyPI.
Stars
452
Forks
138
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Monthly downloads
9,109
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hsahovic/poke-env"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pkmn/ai
The home of competitive Pokémon artificial intelligence
spktrm/porygon2
Porygon2 is a Node.js-based server for simulating Pokémon battles using the pkmn library, as...
poke-AI/poke.AI
An experimental AI that plays the 3rd gen Pokemon games - Winner of Judge's Choice Award for NUS...
pkmn/0-ERROR
Competitive Pokémon battling AI
davidemodolo/alphamon
AlphaMon is a transformer-based Pokemon Showdown doubles AI that combines autoregressive...