Farama-Foundation/MO-Gymnasium

Multi-objective Gymnasium environments for reinforcement learning

What it solves

It provides a standardized way to develop and compare multi-objective reinforcement learning (MORL) algorithms. By offering a consistent API and a set of benchmark environments, it eliminates the need for researchers to build custom interfaces for every new multi-objective problem.

How it works

MO-Gymnasium extends the standard Gymnasium API. While traditional reinforcement learning environments return a single scalar reward, MO-Gymnasium environments return rewards as vectorized numpy arrays, allowing agents to optimize for multiple goals simultaneously. It also includes a LinearReward wrapper that can convert these vector rewards back into a single scalar value using weights.

Who it’s for

It is designed for researchers and developers working on multi-objective reinforcement learning and planning.

Highlights

  • Standardized API for communication between MORL algorithms and environments.
  • Includes a wide range of environments from MORL literature and multi-objective versions of classical environments like MuJoco.
  • Strict versioning of environments to ensure research reproducibility.
  • Compatible with the Gymnasium ecosystem.

Related

  • Project
    Farama-Foundation/Gymnasium

    Gymnasium is a community‑maintained Python library that provides a standard, versioned API for reinforcement‑learning environments (classic control, Box2D, Atari, MuJoCo, etc.). It’s a fork of OpenAI’s Gym and serves as the main platform for developing and benchmarking RL algorithms.

  • Project
    Farama-Foundation/MOMAland

    A Python library for developing and comparing multi-objective multi-agent reinforcement learning algorithms through a standardized API and a set of benchmark environments.

  • Project
    PKU-Alignment/safety-gymnasium

    A scalable and customizable Safe Reinforcement Learning benchmark library providing a standardized set of environments for evaluating safety-constrained AI agents.

  • Project
    Farama-Foundation/PettingZoo

    A Python library for multi-agent reinforcement learning research that provides a standardized API and a diverse set of environments, similar to a multi-agent version of Gymnasium.

  • Project
    Farama-Foundation/Gymnasium-Robotics

    A collection of Reinforcement Learning robotic environments powered by the MuJoCo physics engine and the Gymnasium API for training AI agents in manipulation and navigation tasks.