Who we are

At AgileRL, we are on a mission to democratise access to reinforcement learning for building human-level artificial intelligence systems.
‍
Reinforcement learning, the driving force behind AI systems' planning and decision-making capabilities, will form a part of every sophisticated AI system of the future. However, the immense potential of reinforcement learning is still out of reach for many due to its resource-intensive nature.
‍
AgileRL offers an innovative open-source framework which enables 10x faster training and hyperparameter optimisation over state-of-the-art RL libraries. Arena, the AgileRL RLOps platform, built on this foundation, focuses on streamlining development across the entire reinforcement learning pipeline: simulation, training, deployment, and monitoring.