Farama-Foundation/MiniWoB-plusplus

Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents

Building Open LLM Web Agents with Self-Evolving Online Curriculum RL

🌎💪 BrowserGym, a Gym environment for web task automation

A toolkit for developing and comparing reinforcement learning algorithms.

Simple and easily configurable grid world environments for reinforcement learning

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

An interface library for RL post training with environments.