Jump to content
  • Advertisement


  • Content Count

  • Joined

  • Last visited

Community Reputation

108 Neutral

About sqdejan

  • Rank
  1. sqdejan

    AI User study :)

      Thanks!!! Will look into that.     It's not random (I think you played against MCTS?). It is just more reactive to how you play, trying to figure what is the best move against the current state of the board. I've been inspired by the fixed order from Heroes of Might and Magic, because I thought an AI like MCTS would work perfect in a scenario like that.     Good point, will look into that.
  2. sqdejan

    AI User study :)

      Thanks for the feedback. :) The thing is, today almost all behaviour is created using BT (or some technique similar, like FSM), but the more (machine learning) modern techniques are rarely used, maybe due to their unpredictable nature and being computational heavy. But the progression of computer power allows for more advanced techniques to be used while also, undeniable, sets the expectations for AI a lot higher. This means that hand-coding AI becomes too complex, which requires techniques (such as MCTS) to step in and help. Another thing is, once you figure out how the scripted AI works you can beat it every time. This could potentially be avoided using more modern techniques.   What I compare in my study is how both techniques affect user enjoyment, which I find to be a fair comparison. Both techniques are to be used for the same purpose, control the AI, while behaving differently.   As for whether or not a BT can top MCTS is of course hard to figure out, however, I have found a study showing how a rule-based AI, developed over a period of 10 years, being beaten by a simple MCTS implementation (Integrating Monte Carlo Tree Search with Knowledge-Based Methods to Create Engaging Play in a Commercial Mobile Game). I feel this shows the strength of such a technique.    Another experience I had when implementing the two techniques was the extreme flexibility of adding new units for the MCTS to handle. I just had to specify what the new unit was allowed to do, and the MCTS would take of the rest.
  3. sqdejan

    AI User study :)

    Hi all, currently I'm in the process of making a user study where I try out different AI techniques and see what the effect might be on players. For the experiment I've implemented two types of AI: one using behaviour trees; and one using Monte Carlo Tree Search. The techniques are used in a turn-based tactic game.  I would really love some feedback on what you think. The game has some questionnaires between each AI opponent, and it would amazing if you could play the game 4+ times (a new game will come after each questionnaire). The game can be found here: http://www.janolesen.org/game.html (I think my DNS is down, alternatively use link below)   As the game is made in Unity3D Chrome is unfortunately not an option at the moment. So I suggest you use Safari, Firefox, or (dare I say) IE. Thanks in advance!  
  4. sqdejan

    Evolving Tower Defense

    Thanks for your feedback Servant of the Lord.     Down in the right corner you can open the info sheet again to see what counters what.       There are two arrows in each path but maybe I can animate them so people will see them.      Will look into this.     I have now fixed and uploaded it so it can run in the background. One of the downsides of using an algorithm like this is that it is computational heavy. For version two, there is a reason that it runs significantly faster that I maybe can explain later.     I just tried to see how the most popular TDs on armorgames build their maps, as I first wanted to see if the algorithm will make a game enjoyable before also making the towers/maps unique. I am fan of maze TDs from WC3 and could be nice to make it into that maybe, or have a few levels that have that feature.     I also use them early game but if I have to win I will have to use a combination of all the towers, at least that was how I won version 1.   Final thought:   Maybe people will only see the adaptability of the algorithm if the played the game a lot, but if you want to see it adapt you can try version 1 where you build in first one side, let it evolve, run the wave, sell the tower and build in other side and then let it evolve. It should also be able to figure out what combination of creeps it should send against the towers. At least when I try the same approach of towers in version 1 and 2 I got countered a lot faster in version 1.
  5. Hi all :) I'm currently developing a TD and I would like some feedback at this point. What makes this TD special is that I have tried to use machine learning for adjusting the waves to counter the players current tower setup. I use Evolutionary Programming to figure out what could potentially be the best wave against the players setup after each wave has ended. I hope that this will give a more dynamic game that can adjust to the players playstyle and make him/her reconsider. I have made two versions with different approaches. I have been able to make it through each approach - I had to use some tries to clear version 1 and my record is surviving with 4 lifes. :) After the game is over there is two question that I would like you to answer so I can continue my work.  Thank you in advance and I hope you enjoy. Please feel free to ask questions if you want to know more about the approach. (NB: if you are a Mac user you might know that Unity Webplayer plugin just go outdated with the new Google Chrome update so you will have to use Safari) Version1: www.janolesen.org/evolvingTDv1.html Version2: www.janolesen.org/evolvingTDv2.html
  • Advertisement

Important Information

By using GameDev.net, you agree to our community Guidelines, Terms of Use, and Privacy Policy.

GameDev.net is your game development community. Create an account for your GameDev Portfolio and participate in the largest developer community in the games industry.

Sign me up!