Integrating Reinforcement Learning into a Programming Language.
Christopher Simpkins · 2010
My thesis work combines AI, programming language de-sign, and software engineering. I am integrating rein-forcement learning (RL) into a programming language so that the language achieves three primary goals: accessibil-ity, adaptivity, and modularity. My language, AFABL (A Friendly Adaptive Behavior Language), will be an agent programming language designed to be accessible to non-programming experts like behavioral scientists, game de-signers, and intelligence analysts. If I am successful, my work will enable a discipline of modular large-scale agent software engineering while making advanced agent model-ing accessible to authors of agent-based systems who are not programming experts. There is currently a spectrum of agent-based simulation and programming tools available to social scientists and