An enhanced Proximal Policy Optimization (PPO) algorythm implementation for efficient, robust on-policy sampling in continuous action spaces.. No. of environments: 51

PyFlyt is a flexible library for simulating UAVs in RL, supporting various drone, plane and rocket models and control modes with advanced wind physics and rendering capabilities.. No. of environments: 28

Quantum Circuit Synthesis Environment is a Gymnasium-based framework for RL, designed to optimize the creation of quantum circuits using generative machine learning models. No. of environments: 5

Gym/Gymnasium environments (Reinforcement Learning). No. of environments: 1

A simple 2D racing environment using gymnasium. No. of environments: 3