Interactive Narratives

Teach agents to operate in complex text-based simulations

Two key components in creating effective language-based AI agents are interactivity and environment grounding, shown to be vital parts of language learning in humans, and posit that interactive narratives should be the environments of choice for training such agents. These games are simulations in which an agent interacts with the world through natural language—”perceiving’’, “acting upon’’, and “talking to’’ the world using textual descriptions, commands, and dialogue—and as such exist at the intersection of natural language processing, storytelling, and sequential decision making.



  1. Situated Language Learning via Interactive Narratives
    Prithviraj Ammanabrolu, and Mark O Riedl
    Patterns, Cell Press, 2021


  1. Interactive fiction games: A colossal adventure
    Matthew Hausknecht, Prithviraj Ammanabrolu, Marc-Alexandre Côté, and Xingdi Yuan
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2020
  2. Graph Constrained Reinforcement Learning for Natural Language Action Spaces
    Prithviraj Ammanabrolu, and Matthew Hausknecht
    In International Conference on Learning Representations, 2020
  3. How to avoid being eaten by a grue: Structured exploration strategies for textual worlds
    Prithviraj Ammanabrolu, Ethan Tien, Matthew Hausknecht, and Mark O Riedl
    arXiv preprint arXiv:2006.07409, 2020


  1. Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning
    Prithviraj Ammanabrolu, and Mark Riedl
    In North American Chapter of the Association for Computational Linguistics (NAACL-HLT) 2019, 2019