This is a simple framework for implementing and testing reinforcement learning environments and algorithms

Core interfaces for rl-js: Reinforcement Learning in JavaScript

A collection of various reinforcement learning solver. The library is an object-oriented approach (baked with Typescript) and tries to deliver simplified interfaces that make using the algorithms pretty simple.

Baseline Agent suites for rl-js: Reinforcement Learning in JavaScript

RL Expert skills for Claude Code and OpenAI Codex — 45 reinforcement learning skills covering architecture, algorithms, environments, evaluation, and MLOps.

Classic Control reinforcement learning environments in JavaScript

A JavaScript Environment for Reinforcement Learning.

A library using TensorFlow.js for Deep Reinforcement Learning

reinforcement learning in javascript (fork supporting promises)

Run a trained reinforcement-learning ABR controller (Pensieve-style A3C) as the adaptive-bitrate algorithm in JavaScript video players. Framework-agnostic core + Video.js/VHS adapter.

Othello utility with min/max and reinforcement learning algorithms

Persistent memory system for coding agents with reinforcement learning. Powered by Turso.

WASM-powered reinforcement learning library written in Rust and TypeScript.

A tabular implementation of the SARSA reinforcement learning algorithm which is related to Q-learning

BrothRL - Reinforcement Learning SDK for Voice Agents

A library using TensorFlow.js for Deep Reinforcement Learning

Simple chess engine to play with deep reinforcement learning

**@brain/rl** is a Reinforcement Learning library that implements several common RL algorithms, all with web demos. In particular, the library currently includes:

A Neural Network for Reinforcement Learning in TypeScript

OpenCortex MCP server and CLI for AI agent memory with reinforcement learning and multi-tenant isolation.