After many trials and many grandiose ideas, I simplified everything to bare minimum. Only a single neuron. Fix that part first. I gave up on sophisticated connections, but those functions are still available, gave up on complex distributions. And here I am… a single neuron + 3 input Neurons. The input neurons do almost nothing, they are there to establish input connections with “real” neurons. And without further due, this is it:
I have a pattern of 3 digits but the pattern can be infinite. The learning part comes from repetition. See the same pattern twice and that is it… the third time the pattern is recognized. I taught the AI 2 patterns [1,1,0] and [0,0,1]. Then I asked it for other 3 patterns: [1,0,0], [1,1,1] and [0,1,0]. I was hoping for a “Pattern Unknown”, all over, but instead I got an unexpected: “Pattern recognized !” for pattern [1,1,1]. So if it’s composed of two know patterns, is still considered known.
Keep in mind: NO BACK-PROPAGATION.
I went for an actual neural net, meaning many neurons connected somehow. The full connection (each neuron with each neuron), proved useless, all neurons became symmetric with same output. So next step is to go for an asymmetrical connection between neurons. I’ll first try the asymmetrical_1D and then asymmetrical_2D, and eventually get back to random spherical distribution.
While taking a brake from game development, I though to myself, why not ?? Everybody is doing it ! So I started working on an AI project. Did some literature research for a month or so and then decided what I wanna do. Some sort of a Hebbian type of AI without a correction function (backpropagation).. Well sort of, there is a self correction based on frequency of data and what data is associated with what. Working in Pyhton with the Matplotlib , using, for now, a random spherical distribution for network topology.
Blue -is the input layer, Green dots is the output layer. Trying to learn 3 letters.
We’ve started a small advertising campaign with Google Ads for our new game BackSO. For some reasons I always believed this should be something very costly and maybe complex. Well, it was not. In fact was very simple and the prices were actually very good. You can limit the showings to a certain budget/day, and the budget can actually be very small. Overall I’m very happy with how Google is doing its job. Of course the game is doing rather poorly but that is not because of Google :). For for those of you running small gigs don’t be afraid of Google. You can get very fast some users and if you have the Firebase statistics implemented you can get a very large amount of data for the price of a Starbucks coffee. You can the go on on improving your project of maybe decide to start anew.
I also tried a Fiverr small gig, my conclusion is that it is not worth it. The audience is not targeted and get your money wasted for no real benefit. Better to get with the giants, at least you get some real data that can be used to improve your game, before trying out other campaigns.
For Google Ads, start with a global campaign, all over the world, at the smallest price Google can offer per install. Adjust your game and perhaps do a targeted campaign in richer countries, that perhaps require higher prices for installs but may give you better return on your investment.
We’ve recently published another game on the Google Store: BackSO
BackSO is a casual game to play on short breaks to get your mind off
things. Most levels are strategy based and only few require a bit of eye
hand coordination, but nothing to be scared about. All in good fun.
Your goal is to place all the balls in the correct placement, considering that two balls cannot occupy the same place.
We rushed through and the game is out. I thought I will get some peace and quiet now.. but nooo. It turns out that nobody reads the HELP section. They start the game, fail to even move the character in some cases, get angry and uninstall right away 🙂 The ones that can get the character moving get frustrated because they don’t know what to do next. So I have about 130 player that failed level one several times, and God knows how many uninstalled right away. So I’ve started working hard on a HELP level, this should start once you hit PLAY and then can be replayed from the HELP menu. After two day, I was done and went to a tester. Was I disappointed or what ???
The guy went through the HELP level without reading anything, did at random all the scripted actions then start wondering “How to finish the LEVEL ?” Totally ignored the “BACK” option and got stuck, doing all kinds of actions trying to Finish the level. There are of course many things to learn from this debacle:
People Don’t read.
People want everything to be as it is in other games they’ve played, anything different and they get frustrated and leave.
They want to Win at all cost, no way they’d go through the first level, fail a couple of times and learn how to play..
We don’t really understand our target audience thinking.
No way you drop a game in the Google Store and from the billion of users some will randomly download and try out your game. You would think the probability will work your way and maybe 10-100 people will just download your game at random. The 100 people that downloaded the game, were only users that we kind of brought ourselves directly.
Final details are always stressful. We go through many testing, many alpha, beta and so on, but still some debug coding could be left in the release version, still some minor changes could have some unexpected and unpredictable results in the final product. So, we stress.
Any way I added some tutorials on-line, which can be found here.
The reason is that some of our testers have complained the levels, even level 1 and 2, are very difficult. But other testers went through all levels in under a minute per level. I can’t do that, but I’ve seen other playing and I was amazed with their skill. In fact we re-worked all levels more than 5 times over, to balance things out, but it may be that now, some levels are very difficult to pass for an unskilled player.
Let’s hope for the best and see you on the battle field brave warrior !
Most likely we are not going to make the November 16 dead-line for launch, unless…. Unless I skip the additional testing I had planned. Seems risky though, every change needs to be better tested, since, it seems additional bugs are always just around the corner. A better main menu interface was concocted . I hope to be the final version.
More in game screen shots. Artwork not final though.
I have ten more levels to optimize, 15 are already done. I added a help screen which may be insufficient but we’ll see if I can do more/better by the release date. I’m hoping to upload an alpha version on GPlay by this coming Sunday (28.10.18), so I can send it to other testers, including to a guy who may advice for a better launch campaign. Otherwise my launch campaign has nothing substantial.
On a different note, our team artist has launched his own website to show the world his creations, so, go Ze ! Here is a link: www.pip.pt. Go check it out !
I have tried hosting this website on a free hosting website. So far I have tried : FREEHOSTING and FREEHOSTIA. This is my experience so far:
FreeHosting provides and impressing amount of tools, intuitive, easy to set up. Building an website is a breeze there. A single email account which is fully functional (send and receive, forwarding also works). The bad is that it seems to be offline for very long hours every day. The FreeHosting website would work just fine, I could log in into my control panel , work on my website and such, but my website would be offline . I left FreeHosting after about 3 days.
FreeHostia is now hosting this website. Very limited amount of space compared to FreeHosting, limited traffic, 3 email accounts, which are not actually fully functional. They cannot be used to send emails, just to receive. Very misleading, this should be stated more clearly on their website. The good part is that, the website seem to be up all the time, and fast. I logged an issue with them and I was answered in 2 minutes. That’s unreal. Less tools, less everything, but it is what it says it is, apart from the email issue, and works well.