Adaptive Game AI

Discussion in 'Indie Related Chat' started by vlad, May 9, 2016.

  1. vlad

    vlad New Member

    Joined:
    May 9, 2016
    Messages:
    1
    Likes Received:
    0
    Hello everybody!

    I am thinking of building a generic reinforcement learning platform as a service and I think it has applications in games. Specifically either building AIs to play along/against humans and adapt difficulty/skill of AI on the fly, or model a way to adapt difficulty based on the skill of the player.

    How I think it would work is as follows: the game sends a list of potential actions and a game state (for each AI agent) to the platform (can run locally), and one action is picked. The AI agent performs that action, and sends back an error measure (e.g. new game score, health level, etc.) and the cycle repeats. Models can be pre-trained so they don't play too dumb the first time.

    diagram.png

    The project is at the very beginning. I would like to ask you, the indie game developers, if this is something that you would find useful at all?

    Appreciate the time for reading this and waiting for your feedback or suggestions! Thanks!
     

Share This Page

  • About Indie Gamer

    When the original Dexterity Forums closed in 2004, Indie Gamer was born and a diverse community has grown out of a passion for creating great games. Here you will find over 10 years of in-depth discussion on game design, the business of game development, and marketing/sales. Indie Gamer also provides a friendly place to meet up with other Developers, Artists, Composers and Writers.
  • Buy us a beer!

    Indie Gamer is delicately held together by a single poor bastard who thankfully gets help from various community volunteers. If you frequent this site or have found value in something you've learned here, help keep the site running by donating a few dollars (for beer of course)!

    Sure, I'll Buy You a Beer