Open source alternatives to Pokémon RL
200 open source apps like Pokémon RL, closest match first.
Top picks
- E
Engine
LaunchThe pkmn engine is a minimal, complete Pokémon battle simulation library, written in Zig with a TypeScript reference driver. It aims to be frame-accurate and bug-for-bug compatible with the original game code and with the Pokémon Showdown s
Open source
- H
HandyRL
LaunchHandyRL is a Python and PyTorch framework for distributed reinforcement learning, meant to be applied to your own environments. It focuses on a practical policy gradient algorithm with off-policy correction, which the project describes as a
Open source
- P

Pokerogue
LaunchA Pokémon fangame heavily inspired by the roguelite genre. Battle endlessly while gathering stacking items, exploring many different biomes, and reaching Pokémon stats you never thought possible.
Open source
- S
Snake
LaunchThis is a Python program that plays the game of Snake with AI. The snake moves on a small 6 by 6 grid, and the project implements two strategies. The first uses graph search: when the snake is long enough, it looks for a Hamiltonian cycle t
Open source
- P
Pokete
LaunchPokete is a small terminal game in the style of a well-known monster-catching role-playing game. You travel around a world as a Pokete trainer, catch and train creatures called Poketes, and try to become the best trainer. You start with a s
Open source
- A
AReno
LaunchAReno is a toolkit for reinforcement learning post-training of large language models on a single machine. It covers RL training, SFT and DPO-style training, serving and agentic RL in one self-contained stack. You can go from a base model ch
Open sourceSelf-hosted
More like Pokémon RL
PokeMMO-Online-Realtime-Multiplayer-Game
A simple realtime Pokémon MMO game build with Phaser 3, Colyseus.io & Webpack 4
DeepRetrieval
[COLM’25] DeepRetrieval — Training Search Agent by RLVR with Retrieval Outcome
Pokémon Showdown Randbats Tooltip
Enhanced Tooltip functionality for Pokémon Showdown Random Battle formats
About Pokémon RL
Pokémon RL
Learning Pokémon With Reinforcement Learning
Learning Pokémon With Reinforcement Learning is a research project that trains a reinforcement learning agent to beat the 1996 game Pokémon Red. The authors say they have been developing it since 2020, and that as of February 2025 they could beat the game with a policy under 10 million parameters and minimal simplifications. The site stresses that the output is a technique for producing solutions to Pokémon, not a policy that can play the game in general. It is organized as chapters: an introduction to RL, the environment with its observations, rewards and policy, building and running the system, including reading game RAM and tracking metrics, and concluding thoughts on results and future work. An appendix explains Pokémon battling, the eight badges and field exploration. The code is open source and linked from the site. The page has a changelog that starts with a March 2025 release, and the authors invite contact through a Discord server or by email.
- Price
- Open source
- Category
- Education
- Website
- drubinstein.github.io





