I was looking into getting started with AI and machine learning. As an excuse I wanted to try and make a chatbot centred game.

The idea would be to have the player stuck with a chatbot and only be able to interact or get information about the game world through the AI. Something a bit like Event[0], but without any graphics whatsoever. Basically an advance gamebook, or a role-playing game where the game master is an AI. Trying to replicate a simple murder mystery would be a start.

Would it be feasible ? Would an AI be able to create an adventure from scratch with just a few random seeds ? Could I train the AI using film or game scripts ?

How long would it take? Am I signing myself up for 2 years of coding ?

Are there any opensource AI which can be downloaded and trained ?

What key issues do you think I overlooked ? As I said I don't know much about machine learning. I have done two simple games using Pygame so far, a Zelda like and a Space Explorer, in both the AIs where scripted.


2 Answers 2


Would it be feasible?

In short: yes, theoretically.

Long answer: It's going to take a while and it will be a lot of trial and error until you know what your doing then you have to figure out how to make the output from the machine learning make sense (I can almost guarantee it's going to butcher whatever language your going to try and teach it, at least for the first few attempts). It might be worth looking into making it detect what kind of tone you said it in, then generate a pre-defined bit of text in response. For example if someone if being a dick you might be harsh or possibly leave out a bit of information to make it harder for the player.

How long would it take?

Depends. what level of interaction do you want?

If you want every possible combination of words to be recognised properly you could be sat there for decades creating the singularity... On the other hand if you only want basic chat functionality you could have it done in a few months.

People have been trying to make proper chat programs for ages (at least 50 years) all of the attempts have taken a long time and produce mediocre results but on the other hand they are trying to make a program that is able to hold conversation to the level of the turing test. If you limited the scope and concentrated on building some way of extracting key words from the sentence then feed that into the machine learning portion you might be able to make something similar to what you want.

Are there any opensource AI which can be downloaded and trained?

There are a few out there but I don't know enough about them to tell you which ones would be good for this application.

Lucida AI, a program to make a virtual assistant think google search only locale on your machine.

Mahout, appears to be a library to enable scale-able machine learning. So you might want to look into this for the actual learning part as it should be able to scale so that you can get it to "learn" faster. small plus is that it's an Apache project so you can use it a for commercial software.

personally i'd take a small course into machine learning to see what your getting into to see if you could possibly stand spending an extended period of time developing. Udacity has a free course on it for deep learning which is a branch of machine learning or if your really dedicated this course specifically for machine learning however it costs a bit of money (200 USD with a 50% discount if you complete the course in a year).

What key issues do you think I overlooked?

In the end if your still going to make a game after going to all the effort of this, is it going to be a game that is "fun" or at least a game which will be an interesting and fun experience for the player that won't know the backstory of you developing an AI from the ground up. Will there be enough content to keep people engaged with it?

How are you going to get the AI to naturally get across narrative to the player without making it sound forced. An exelent example that i heard recently was that some scientists looked at a bunch of data and found a correlation between amount of Ice cream sold and people drowning. Someone without knowledge might think that they are linked but with context you realise that it's Summer and people are hot so they eat Ice cream and go swimming. How would your program deal with the context of the story without jumping to extremely strange conclusions?

What do you expect the player to be using to run the game? As far as i know must methods for interacting with such an AI that you want to develop required quite high end hardware. While most of this will be dependant on you training it (I assume) that there will still be a significant burden on players CPU if they expect to have good response times. You could try offsetting this by using the GPU to do some of the work (see CUDA CUDINN and OpenCL).

What happens when the game is running on a netbook without a GPU? could you get away with adding some story element that would allow for long waiting times between responses? on a different plant to the person that your talking too so you have to wait for the signal to reach them and travel all the way back? (As for as i can remember Earth to Mars is around 12 mins?)


I'd also look into old text only games to see how they do it. I think most of they are just multiple choice but some of the lucusArts games had a small box were you could type in a question and based on some keywords it would give you a different response than the standard dialog options. Look into those and think about how an AI would improve those scenarios, Zork, Colossal Cave Adventure, etc. there are lots that have been ported to browser so you can just try them for a bit to get a feel of how they work.

  • \$\begingroup\$ Another resource that may be of use is this Gamasutra article on markup languages for chatbots - even if you don't hand-author the bot's responses this way, it could prove a useful starting point for how to process the bot's input and structure its flow. \$\endgroup\$
    – DMGregory
    Sep 20, 2016 at 3:13

Would it be feasible?

Probably. As for making seeded adventure plots, there is some background that needs to go into this. Your AI must first be able to communicate the plot, so there must be some pre-formulated sentences it can use to describe plot elements. Also, the bot needs to be able to determine a good plot from a boring one, so you might need to hard code in things like adventure length and difficulty. Training it using film scripts? This is a much bigger project. In theory, it could probably be done, but in practice you'd have to run many scripts through it, and your training program would have to be able to identify protagonists and plot devices, which can sometimes be very subjective (try running the script of Primer).

How long would it take?

This depends on your level of coding knowledge. If you're just starting out, I wouldn't recommend such a project, unless you don't plan on finishing it. You might learn a lot on the way, but if you don't already understand it, you'll get bored quickly.

If you are experienced, this could still take a while, possibly years depending on how much of your spare time you want to dedicate to it. There are several coding challenges I can see just from your proposal, and most of them have to do with the difficulty of programming an AI that learns anything. Whole teams of people work on projects that make AI's identify species of birds based on their pictures, so delegating that amount of work to one person is a lot to do.

Are there any open source AI that can be trained?

A quick Google search will result in a few:

TensorFlow - Open source, Python

Tweety - Open source, Java

Linas Vepstas' site lists a few others

I just found these quickly, so I don't know what application they'll have to you without more specifics about the language you plan on coding in and your coding philosophy and practices.

What key issues do you think I overlooked?

The complexity of this level of AI. You can't just tell a program to learn and create, you have to give it a ton of information and guidelines. It takes months of experimenting to find things that work well, and even then, your AI can mess up. If you're not familiar with the hard science and math behind AI, I wouldn't suggest you go about trying to implement one in your game unless you really know what you're doing.


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .