Hey just joined the community. I'm currently a python/golang dev learning rust and already love the language but have honestly no experience in game dev.

Hey there! Welcome to the community. In a lot of ways game dev isn't that different from other kinds of programming, so you can just pick up how things work as you go. That's what I do with pretty much everything. :)

I'll start learning Bevy, the website have some good tutorials it seems.

Another great resource to have on hand is the unofficial [Bevy Cheatbook](https://bevy-cheatbook.github.io/).

I'm sure all you pros already making multiplayer games on godot

Hi @Zicklag! You might remember me from the WASM / ECS / Flecs discussions (I maintain flecs-polyglot). I noticed you liked this repo recently (https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers) about Bayesian probabilistic programming. I was wondering what your current interest is in this topic, and if you've heard about active inference and the free energy principle. I also currently work in this field. I was wondering if you had any thoughts about using deep learning AI for game AI / NPCs, and would love to discuss it with you, as well as how we can implement it, either with current LLMs / reinforcement learning or in the future with a Bayesian neural network.

Hey @rou, yeah I remember. :)

I have a funny relationship with machine learning.

I've known a bit about it for years, read quite a few tutorials, pieces of courses, books, etc., but not really gotten enough time to focus on it and do any real experimenting, which means my practical know-how is pretty low.

I've just like day-before-yesterday decided that I'm going to have to start just experimenting with stuff, even if I don't understand all the theory.

I don't have a heavy math background, so while I'm competant in general and can make sense of a lot of stuff, even the notation in some cases, I lack context.

I just discovered Gaussian Processes through the [chapter in the D2L course](https://d2l.ai/chapter_gaussian-processes/index.html), and thought they seemed really cool, and searching for that on GitHub brings up some stuff on Basysian Optimization, and searching for that brough up that book, which I read half or so of the first chapter to get the basic idea.

In summary, I'm not probably good at any of it ( yet! ), and desperately lacking practical experience, but I have a great interest in it, and would be happy to discuss things, still!

I want to get my hands dirty and actually start making things, and I could definitely use that for at least Jumpy AI, which is going to need some real improvement eventually.

@kimbring2 has worked a lot with AI in games.

For deep learning in Rust, I've tested

burn

, but [

dfdx

](https://github.com/coreylowman/dfdx) is really, really nice so far.

It's extremely ergonomic and easily extensible with custom modules for building neural networks.

I wanted to get started with some basic reinforcement learning with it.

They've already got a couple RL examples.

I feel like reinforcement learning fits best in the context of games from what I've ready so far ( in the context of deep learning, not counting other game AI techniques ).

I couldn't get a feel yet for how Baysian neural networks would compare practically to alternatives.

@Zicklag I'm in the same boat as you 🙂 I'm a general software engineer, but I recently started working for an AI startup, which has given me a chance to work with a lot of brilliant ML engineers and neuroscientists implementing their work, and have had to accelerate my understanding of AI programming which I always had an interest in but never had the time / justification / confidence until recently. I'm also on the long journey of re-learning math so that I can eventually get to the more advanced ML related math. Recently I've started a group of neuroscientists, engineers and game devs trying to utilize deep learning AI for games, currently with LLMs but eventually with active inference (Bayesian neural network) and take the same ideas from active inference to try to apply them to our current technology in the meanwhile, but I'm not trying to solicit anything, and I know you're very busy, so I'll keep you in the loop over time and then you can tell me if you're ever interested in joining / collaborating! Those of us who are less experienced in ML / DL are also on the journey of learning more about AI through developing this project. With active inference (which uses Bayesian methods), there is a very real possibility that we can reproduce sentient / human intelligence, or at least something indistinguishable from it. This would also be happening actively, like a game loop. I highly recommend watching these relatively short videos by my Chief Scientist and Director of Research at the startup I work for to explain why, and I think when you watch these videos it will be intuitively obvious why when this is implemented it will be significantly more advanced than reinforcement learning, and it's potential application in games:

Very cool! I'll take a look into it if I get the chance for sure, thanks for the links.

Sounds good!

As far as joining / collaborating, where do you guys communicate in general? Are you on GitHub? I assume you have a Discord server or something?

It's a Discord server currently yeah, there will be a GitHub soon. I'm not trying to advertise on your Discord, but if you want the link feel free to let me know. 🙂

I work on a "Family Mode" computer 95% of the time, where I can't get to Discord ( I'm accessing this one over a bridged server with a whitelisted domain ), but I might join sometime in the 5% that I'm not. We're pretty nice around here so I doubt anyone minds too much if you post your Discord link, but you could send it to me at zicklag at katharostech dot com in case that's something to avoid.

Okay, sounds good. I just didn't want to come off like I'm just joining your Discord to advertise one of my servers, but that being said there is no exclusivity currently, and anyone else who is interested in this topic is free to join as well, and maybe I can set up a bridge for you sometime: https://discord.gg/fdBpwGd2

Awesome, thanks!