Towards Procedurally Generated Languages for Non-playable Characters in Video Games
Joshua Sirota, Vadim Bulitko, Matthew Robert Graham Brown, Sergio Poo Hernandez · 2019 IEEE Conference on Games (CoG) · 2019
Non-playable characters (NPCs) enhance a player's immersion in a video game. Communications among NPCs create atmosphere and, in some games, are a core element of the gameplay. Yet, the majority of games manually script inter-NPC communications creating only an illusion of such exchanges. Doing so is laborious and results in fixed interactions which may not respond to the player's actions or changes in the environment. In this paper we propose procedural content generation (PCG) for emergent inter-NPC languages. Indeed, recent research demonstrated that deep neural networks can be trained to develop an artificial language to communicate with each other. The work used a fixed, handcrafted network architecture identical for both the sending and receiving agents. We extend the work by using neuroevolution for both the sender and the receiver. In doing so we evolve both the architecture and weights of the agents and show that they successfully develop novel languages to communicate among themselves.