Corpus ID: 173990703

Towards Interactive Training of Non-Player Characters in Video Games

@article{Borovikov2019TowardsIT,
  title={Towards Interactive Training of Non-Player Characters in Video Games},
  author={Igor A. Borovikov and Jesse Harder and Michael Sadovsky and Ahmad Beirami},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.00535}
}
  • Igor A. Borovikov, Jesse Harder, +1 author Ahmad Beirami
  • Published in ArXiv 2019
  • Mathematics, Computer Science
  • There is a high demand for high-quality Non-Player Characters (NPCs) in video games. Hand-crafting their behavior is a labor intensive and error prone engineering process with limited controls exposed to the game designers. We propose to create such NPC behaviors interactively by training an agent in the target environment using imitation learning with a human in the loop. While traditional behavior cloning may fall short of achieving the desired performance, we show that interactivity can… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 21 REFERENCES

    From Demonstrations and Knowledge Engineering to a DNN Agent in a Modern Open-World Video Game

    VIEW 1 EXCERPT

    Interactive Training (code base)

    • I. Borovikov
    • https: //github.com/nekkar/interactive_ training,
    • 2019
    VIEW 2 EXCERPTS

    Human-Like Playtesting with Deep Learning

    VIEW 2 EXCERPTS

    Imitation Learning with Concurrent Actions in 3D Games

    VIEW 1 EXCERPT

    Shared Autonomy via Deep Reinforcement Learning

    VIEW 2 EXCERPTS

    Generative Adversarial Imitation Learning

    VIEW 2 EXCERPTS

    Generative adversarial imitation learn

    • J. Ho, S. Ermon
    • 2016
    VIEW 2 EXCERPTS