Skip to content
Pokémon RL

Open source alternatives to Pokémon RL

200 open source apps like Pokémon RL, closest match first.

Top picks

  1. E

    Engine

    Launch

    The 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

  2. H

    HandyRL

    Launch

    HandyRL 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

  3. P

    Pokerogue

    Launch

    A 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

  4. S

    Snake

    Launch

    This 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

  5. P

    Pokete

    Launch

    Pokete 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

  6. A

    AReno

    Launch

    AReno 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

7
P

PGX

Vectorized RL game environments in JAX

Launch
8
T

TextRL

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback)…

Launch
9
P

PokeMMO-Online-Realtime-Multiplayer-Game

A simple realtime Pokémon MMO game build with Phaser 3, Colyseus.io & Webpack 4

Launch
10
O

Open Spiel

OpenSpiel is a collection of environments and algorithms

Launch
11
O

OpenHome

Application for importing and transferring Pokémon between save files

Launch
12
P

Pikachu Volleyball

Pikachu Volleyball reimplemented in JavaScript

Launch
13
P

PokeTokenBar

Use your tokens to raise, evolve, and collect Pokémon!

Launch
14
I

Inno Agent

An open-source personal learning agent with three-layer memory

Launch
15
P

PKVault

Centralized Pokémon storage management & Pokedex app

Launch
16
P

Pokemon Showdown

An online pokemon battle versus game

Launch
17
V

Vibrant Labs

Autonomously scaling environments

Launch
18
A

ASE

Adversarial skill embeddings for training reusable controllers

Launch
19
P

Pokeclicker

The new and improved version of the popular idle/incremental PokéClicker

Launch
20
P

PKVault

Pokemon storage and save manipulation tool

Launch
21
O

openclaw-rl-training

OpenClaw-RL framework for training personalized AI agents

Get
22
D

DeepRetrieval

[COLM’25] DeepRetrieval — Training Search Agent by RLVR with Retrieval Outcome

Launch
23
P

Pokémon Showdown Randbats Tooltip

Enhanced Tooltip functionality for Pokémon Showdown Random Battle formats

Launch
24
N

Nnue Pytorch

Stockfish NNUE (Chess evaluation) trainer in Pytorch

Launch
25
D

Docs

Documentations for PaddlePaddle

Launch
26
P

Pyre Code

A self-hosted ML coding practice platform

Launch
27
L

Labml

Monitor deep learning model training and hardware usage from your mobile phone

Launch
28
J

Jumping-Agent-platform

Build your own AI agent through gameplay

Launch
29
M

MimicKit

A lightweight suite of motion imitation methods for training controllers

Launch
30
A

Alpamayo Recipes

Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for…

Launch
31
P

Polishedcrystal

An upgrade to Pokémon Crystal

Launch
32
C

CatchTwo

The ultimate open-source Pokétwo autocatcher

Launch
33
R

RPG-ZeroRepo

[ICLR 2026] RPG: A Repository Planning Graph for Unified

Launch
34
P

Polished Map

A map and tileset editor for pokecrystal, pokered, and projects based on them

Launch
35
F

FinRL-Meta

FinRL­-Meta: Dynamic datasets and market environments for FinRL

Launch
36
O

Optuna Dashboard

Real-time Web Dashboard for Optuna

Launch
37
P

Pokeapi.co

The PokéAPI documentation website

Launch
38
N

Neural Network Chess

Free Book about Deep-Learning approaches for Chess

Launch
39
B

BALROG

Benchmarking Agentic LLM and VLM Reasoning On Games

Launch
40
T

Transformerlab App

The open source research environment for AI researchers to seamlessly train

Launch
41
C

Code2Video

[ICML 2026] Video generation via code

Launch
42
P

Pokedex Angular App

Offline compatible Progressive Web Application

Launch
43
A

Agents From Scratch

Build AI agents from first principles using a local LLM

Launch
44
M

MedicalGPT

Training Your Own Medical GPT Model with ChatGPT Training Pipeline

Launch
45
P

Pikachu Volleyball P2p Online

Pikachu Volleyball peer-to-peer online via WebRTC data channels

Launch
46
A

Agentpet

A desktop pet for macOS & Windows that monitors your AI coding agents

Launch
47
L

Llama TRL

LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA

Launch
48
H

HappyTorch

A PyTorch coding practice platform — covering LLM, Diffusion, PEFT, and more…

Launch
49
C

CheatRunner

Web-Based Cheat Trainer for PS5!

Launch
50
V

Von

The open-source System One decision model

Launch

About Pokémon RL

P

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