# \[Dev\] AOE:DeepDE **URL:** \ **Category:** II - Modding\ **Created:** [February 1, 2020, 6:45am UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257 "2020-02-01T06:45:30Z")\ **Posts on this page:** 14\ **Page:** 1
**Author:** ![DomeCitron2509](https://forums.ageofempires.com/letter_avatar_proxy/v4/letter/d/839c29/32.png) [@DomeCitron2509](https://forums.ageofempires.com/u/DomeCitron2509)\ **Post date:** [February 1, 2020, 6:45am UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/1 "2020-02-01T06:45:30Z")
Good morning, everyone, I’m a computer developer and I’m passionate about artificial intelligence. So you probably understood the subject of this topic, being a developer you’ll also think that I’ll talk about programming flaws, or current problems with the game, this is not the subject so please disregard this side (I’m just warning you). Today I’m calling on the community to push the devs to create an API in a common language (Python, C++, Rust…) that will allow us to develop a powerful AI based on current research (Basically Q-Learning, Long Short Term Memory, Reccurent Neural Network, Genetic Learning etc…) because yes your language is cool but no. Why not? Because : - It doesn’t allow us to have matrix or variable (float & numpy etc…). - Well, I won’t explain more about why because the first point defines everything. Conclusion: I think that the game offers new availability to AI, that SC2, on this one the micro-management is “faster”, the decision making less punitive due to the production time or the harvest time which is “shorter”, the fact that there are only 2 resources, 3 civ and that the maps are “smaller”. We have DeepMind AlphaStar which are a real masterpiece. But I am convinced that AOE II will not be as “easy” to implement because for me AOE II is much more punitive, in the sense that the game is slower and we have more stratagem to carry. This means that the complexity of the choice of the strategy to apply at time T is much more difficult and varies much more than on SC2 which is more monotonous. Moreover it will allow to learn new technique, new approach, new build order, even beat the top ladder, which will motivate many players, because an AI better than the top 1, allows us to hope to be one day 🙂 So let’s get out this API ! Let’s show what AOE:II’s devs are up to. Thanks for reading. Please support us with a comment or a question. ---
**Author:** ![Szaladon](https://forums.ageofempires.com/user_avatar/forums.ageofempires.com/szaladon/32/114743_2.png) [@Szaladon](https://forums.ageofempires.com/u/Szaladon)\ **Post date:** [February 4, 2020, 1:22pm UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/2 "2020-02-04T13:22:45Z")
I want to see an AI which beats The Viper or DauT 1vs1 XD ---
**Author:** ![Yorok0](https://forums.ageofempires.com/user_avatar/forums.ageofempires.com/yorok0/32/29229_2.png) [@Yorok0](https://forums.ageofempires.com/u/Yorok0)\ **Post date:** [February 4, 2020, 4:13pm UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/3 "2020-02-04T16:13:26Z")
AIs APM needs to be limited. Else it just abuses its infinite APM by exploiting ranged units (especially monks). APM of Starcraft 2 AlphaStar AI was limited in order to make it play more similarly to humans. It is also more interesting if AI wins by being smart, not by doing 10 000 things in one second. ---
**Author:** ![DomeCitron2509](https://forums.ageofempires.com/letter_avatar_proxy/v4/letter/d/839c29/32.png) [@DomeCitron2509](https://forums.ageofempires.com/u/DomeCitron2509)\ **Post date:** [February 4, 2020, 4:43pm UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/4 "2020-02-04T16:43:17Z")
Exactly, the goal would be that with less apm than a player she would be able to win the game, because we do a lot of useless apm. Look at this schematic where we can see some real “Human” behavior. [![](https://cdn.ageofempires.com/aoe-forums/original/3X/4/a/4aef83afdb90319d5274a6c24e0b0d8ab1855656.png) ](https://cdn.tomshardware.fr/content/uploads/sites/3/2019/01/scii-blogpost-fig09-width-1500.png) ---
**Author:** ![DomeCitron2509](https://forums.ageofempires.com/letter_avatar_proxy/v4/letter/d/839c29/32.png) [@DomeCitron2509](https://forums.ageofempires.com/u/DomeCitron2509)\ **Post date:** [February 9, 2020, 6:09pm UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/5 "2020-02-09T18:09:31Z")
Here’s what you need to know, here’s what you need to practice! Thank you for your support. If you want to communicate with me, mp I will give you my discord. - [https://github.com/cair/deep-rts](https://github.com/cair/deep-rts) - [https://github.com/Stolym/Lead-Lord](https://github.com/Stolym/Lead-Lord) - [https://www.youtube.com/watch?v=jtlrWblOyP4](https://www.youtube.com/watch?v=jtlrWblOyP4) ---
**Author:** ![DomeCitron2509](https://forums.ageofempires.com/letter_avatar_proxy/v4/letter/d/839c29/32.png) [@DomeCitron2509](https://forums.ageofempires.com/u/DomeCitron2509)\ **Post date:** [April 28, 2020, 6:04pm UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/6 "2020-04-28T18:04:42Z")
Hey, everybody, I’m doing a little up with some basic features I’ve created. I hope you’ll like it! > **[Stolym/SimpleNeuralNetwork](https://github.com/Stolym/SimpleNeuralNetwork)** > > Here you can find how to make a simple neural network ! - Stolym/SimpleNeuralNetwork > **[Stolym/MetaSimpleNeuralNetwork](https://github.com/Stolym/MetaSimpleNeuralNetwork)** > > Meta-Learning. Contribute to Stolym/MetaSimpleNeuralNetwork development by creating an account on GitHub. Haste to have an answer from the developers on an API. “A little star for the support” 🙂 ---
**Author:** ![Yorok0](https://forums.ageofempires.com/user_avatar/forums.ageofempires.com/yorok0/32/29229_2.png) [@Yorok0](https://forums.ageofempires.com/u/Yorok0)\ **Post date:** [April 30, 2020, 12:57am UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/7 "2020-04-30T00:57:49Z")
You are just learning about neural networks, but haven’t done anything related to AOE 2 yet? ---
**Author:** ![b9thirty99](https://forums.ageofempires.com/user_avatar/forums.ageofempires.com/b9thirty99/32/104266_2.png) [@b9thirty99](https://forums.ageofempires.com/u/b9thirty99)\ **Post date:** [April 30, 2020, 1:50am UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/8 "2020-04-30T01:50:39Z")
■■■■ yeah. I don’t know what you talked about, but it sounds cool and community friendly. So +1! ---
**Author:** ![DomeCitron2509](https://forums.ageofempires.com/letter_avatar_proxy/v4/letter/d/839c29/32.png) [@DomeCitron2509](https://forums.ageofempires.com/u/DomeCitron2509)\ **Post date:** [April 30, 2020, 3:26pm UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/9 "2020-04-30T15:26:16Z")
Exactly, it’s to keep you informed 😉 I think I have found a solution to create a Recurrent Neural Network, with the game recs. This allows us to have an ai to create the best build order of the game ! So don’t hesitate to contact me if you want to participate! ---
**Author:** ![DomeCitron2509](https://forums.ageofempires.com/letter_avatar_proxy/v4/letter/d/839c29/32.png) [@DomeCitron2509](https://forums.ageofempires.com/u/DomeCitron2509)\ **Post date:** [April 30, 2020, 3:32pm UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/10 "2020-04-30T15:32:08Z")
Ahah thank you for your support! We’re talking about a more advanced method for artificial intelligence, like unbeatable. ---
**Author:** ![KUKUZAVRIK6897](https://forums.ageofempires.com/user_avatar/forums.ageofempires.com/kukuzavrik6897/32/32950_2.png) [@KUKUZAVRIK6897](https://forums.ageofempires.com/u/KUKUZAVRIK6897)\ **Post date:** [April 30, 2020, 9:13pm UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/11 "2020-04-30T21:13:13Z")
Go for it!!! Thank you! ---
**Author:** ![WakelessShelf23](https://forums.ageofempires.com/user_avatar/forums.ageofempires.com/wakelessshelf23/32/28810_2.png) [@WakelessShelf23](https://forums.ageofempires.com/u/WakelessShelf23)\ **Post date:** [June 21, 2020, 9:27pm UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/12 "2020-06-21T21:27:57Z")
How can I help, brother? ---
**Author:** ![SaladEsc](https://forums.ageofempires.com/user_avatar/forums.ageofempires.com/saladesc/32/42482_2.png) [@SaladEsc](https://forums.ageofempires.com/u/SaladEsc)\ **Post date:** [July 21, 2020, 10:03am UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/13 "2020-07-21T10:03:11Z")
A machine learning based AI very difficult to pull off for aoe2, but recording hotkey key presses and mouse clicks from experts games, and train it based on that data could be a start. These can be extracted from rec games The challenge is also that there needs to be a ‘fitness’ in order to steer the AI in the right direction. Ultimately this needs to be ‘winning the game’ vs ‘loosing the game’ but this seems too far stretched since aoe2 is: > [@DomeCitron2509](#): > > much more punitive, in the sense that the game is slower and we have more stratagem to carry ---
**Author:** ![Orine7](https://forums.ageofempires.com/user_avatar/forums.ageofempires.com/orine7/32/32378_2.png) [@Orine7](https://forums.ageofempires.com/u/Orine7)\ **Post date:** [September 29, 2020, 2:42am UTC](https://forums.ageofempires.com/t/dev-aoe-deepde/69257/14 "2020-09-29T02:42:43Z")
Hey, I’m here to try helping this issue, have you created a repository ? If not, let me create one to upload our possible solutions. I’m tryin to “replicate” the same way that sentdex did with his “Ai plays gta v” series, you should check out. I think that the hardest challenge is to retrieve real time info about the game, did you came up with somithin?