Page 1 of 1

Suggestions for games that use NPCs powered by a new type of AI that replicates creativity

Posted: Fri May 04, 2018 2:04 pm
by Dromo
I am about to start a PhD that will investigate ways of replicating creativity in the AI systems of simulated people in virtual environments. I will research which psychology theories and models to use in order to achieve this, with a focus on creative problem solving.

The aim of this project is to create virtual characters and NPCs that can create new solutions to challenges, even if they have never encountered these before. This would mean that not every possible action or outcome would need to be coded for, so less development resources are required. Players would encounter virtual people that are not bound by rigid patterns of pre-scripted behaviour, increasing the replay value and lifespan of games, and the accuracy of simulations.

I am looking for companies or organisations that would be interested in working with me on my PhD, and I think computer games companies might be the most likely. I am trying to think of ways in which this new AI system might benefit games companies, or improvements and new types of games that might be possible. I am on this forum to ask for your thoughts and suggestions please, so I can approach games companies with some examples.

Thank you for your time and interest.

Re: Suggestions for games that use NPCs powered by a new type of AI that replicates creativity

Posted: Sat Dec 01, 2018 1:14 pm
by Baillargeon
Can you link to this AI, Dromo? Who is developing it? I'd like to know more.

Re: Suggestions for games that use NPCs powered by a new type of AI that replicates creativity

Posted: Thu Dec 13, 2018 7:51 pm
by Alvaro
I'm curious to know what you have discovered in the months since the first post.

I suspect that Psychology won't have anything illuminating to bring to the table. DeepMind's Alpha Zero's playing style is often described as creative, but I think that's just a descriptive label we assign, and not something that can be added as an ingredient to a program.

If your agents make a mental list of actions they can take, they score them and then pick the one with the highest score, you have what's called a "utility-based architecture". The score they are maximizing is called "utility" (although technically this should be "expected utility", if you want them to reason under uncertainty). This architecture is in some precise sense the only rational approach to making decisions, and if your agents are good enough at estimating the expected utility of their actions (the expected sum of the future stream of rewards), they might seem intelligent and even creative.