Adversarial Reinforcement Learning for Procedural Content Generation

no code implementations • 8 Mar 2021 • Linus Gisslén, Andy Eakins, Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar

We present a new approach ARLPCG: Adversarial Reinforcement Learning for Procedural Content Generation, which procedurally generates and tests previously unseen environments with an auxiliary input as a control variable.

reinforcement-learning Reinforcement Learning (RL)