4 ай бұрын
7 ай бұрын
8 ай бұрын
2 жыл бұрын
Пікірлер
@okaneskin9536 Күн бұрын
thanks a lot. I've been having a lot of problems with ml agent for a few days. When I followed what you did it worked flawlessly.
@MagicStudioEu 3 күн бұрын
Thank you!!
@MagicStudioEu 3 күн бұрын
Thank you very much!
@sugarblock-nd6pw 7 күн бұрын
nice video!
@keithdavis969 8 күн бұрын
Thank you for the updated info on MLAgents. It seems that most info I find (even pre-release books) tend to be riddled with errors due to ever more recent changes. Will there be a playlist? Looking forward to more!
@LudicWorlds 7 күн бұрын
Yes I will be continuing this series in the new year.
@niocrongames-gamedevcoding4250 9 күн бұрын
nice tutorial, thanks =)
@niocrongames-gamedevcoding4250 9 күн бұрын
thanks for the tutorial, looking forward to part 3 =)
@jophanshaji554 10 күн бұрын
Your videos are incredibly helpful, and they have been a great resource for my project. If you could post the next one soon, it would be very demure of you. I’m eagerly looking forward to it!
@TIHiHubMixedRealityLab 11 күн бұрын
Helped a lot!!!!!!!!!!
@ardhenismuhammadaflah7818 14 күн бұрын
Man, i love this so hard to find this tutorial rn
@康博-y7e 15 күн бұрын
Is this code file something that requires payment to access?
@康博-y7e 15 күн бұрын
Is this code file something that requires payment to access?
@nadiadwi4966 16 күн бұрын
This is the outline effect I was looking for, very helpful video!
@carson9395 20 күн бұрын
Thank you very much for the tutorial, you're a lifesaver. This was very clear and understandable, I often found myself pausing to ask myself a question only to unpause it and have you answer the question right after. Great job 👍
@AntonioJavierSánchezLópez 22 күн бұрын
Someone knows How to do the play mode without have to do the build all the time?
@mouse2708 22 күн бұрын
Finally 😃 thanks for dropping the video
@sagrgywejhxcvx 24 күн бұрын
How to run not that specific Project? How to run my own?
@sagrgywejhxcvx 24 күн бұрын
If I already downloaded anaconda IDE than should I download miniconda? And also I wanna say thanks for such high quality tutorial Edit: you can use Anaconda IDE, but its size is 20gb
@emmabarrios7705 27 күн бұрын
This is amazing! for some reason I have troubles getting controller tracking and input, tested with Oculus integration and MetaXR all in one as well since the former was deprecated, it works perfectly on the device once deployed though, great work!!
@devarshify 29 күн бұрын
i would like to spawn furniture prefabs inside their respective bounding boxes, can you help me with a method to achieve this please. ARBoundingBox does not expose a variable that gives its centre
@mouse2708 Ай бұрын
Thank you for this tutorial Looking forward for the upcoming videos.
@ryanyao7732 Ай бұрын
Btw, do you think it is a feasible way to first generate an executable environment from unity rather than training directly in the Unity hub editor (with duplicate agents for parallel training) and then train the MLAgent for faster training?
@LudicWorlds Ай бұрын
Apparently so (although I've not tried it yet myself), check out this link: unity-technologies.github.io/ml-agents/Learning-Environment-Executable/
@ryanyao7732 Ай бұрын
@@LudicWorlds Thank you for the reference!
@ryanyao7732 Ай бұрын
Hey just want to say thank you for this video and I am really looking forward to the upcoming videos. I do hope that the topic of self-defined environments can be included.
@dylanbinu9034 Ай бұрын
Without a doubt, the best tutorial I have watched on Mixed Reality with Meta Quest 3. Seriously. All concerns were addressed in such an efficient manner and every 5 second interval held valuable information. Thank you for taking the time to make this.
@buyukpotron9613 Ай бұрын
you are the best . thank u
@je4a301 Ай бұрын
Hey, are you going to do a full fledged series of this? I’m looking into training robots (robocup football small size) using unity ml agents but most learning resources being old end deprecated scared me. You would be a life saver
@LudicWorlds Ай бұрын
Yes, I will indeed be making a series of videos on ML-Agents. I'm going to get back to making videos on this shortly, and will be focusing on the series for the remainder of this year.
@Helder-Muge Ай бұрын
I think just clicking on the claim megascans doesn't actually give all the megascans, it gives the opportunity to have all the megascans, but doesn't actualy give all the megascans to actualy have all the megascans it's necessary to add every single asset to the library because only when you add the asset to the library it is when it says that it is owned and not just "From Free" being the "From Free" an indication that you can get it for free but you don't have it yet.
@LudicWorlds Ай бұрын
I also suspect that this may be the case; it's certainly not entirely clear.
@geefhotmail6311 Ай бұрын
Thanks man!
@cadensam7 Ай бұрын
OMG YES AND TELL ALL YOUR GAMING FRIENDS Many have an Epic account
@Skarredghost Ай бұрын
Amazing!
@jeffg4686 Ай бұрын
Nice - a lot of questions come to mind. Why now? Why only until Dec 31st? How many can you download? Are they still an asset for you after dec 31 if you claim them before then, or do you have to download by then? Are they closing up shop or trying to get more business?
@LudicWorlds Ай бұрын
I guess they a using the giveaway to draw attention to their new marketplace. The FAQ suggests that any assets that you 'claim' remains yours for free, beyond 2024. However, on the unreal forums, there seems to be some confusion as to whether you need to add each asset to your library, in order to retain them: forums.unrealengine.com/t/do-i-need-to-press-add-to-library-on-fab-for-every-asset-once-i-claim-them-for-free/2086597/5 One of the forum admins has said that they will "reach out for a full clarification". I'll keep an eye on the post. 👀
@AliMusllam Ай бұрын
Because after Dec 31 the bussiness model will change slightly, not sure what is exactly, but will be like paid model to have new assets every month. However, if you take them now, you will have them forever (but not including the future assets), unlimited download, for any engine . It seems this is good to be true, but this just a marketing move for their new marketplace Fab, since they are looking to dominate any 3D related assets space, even challenging Unity Asset store for Unity users.
@fawful56 Ай бұрын
Does this work for quest 2 as well? I know the camera is not as good, but will it work?
@manuelmeekattukulam Ай бұрын
Great tutorial!!!
@SPILLINGSHADE Ай бұрын
i cant install python-3.10.12 help?
@vrfxrealtime Ай бұрын
thanks for sharing!
@fabis9734 Ай бұрын
Great Video! Extremly helpful to get started with ML-Agents! Hope more content regarding this topic is coming sooner then later :)
@aksharmaharaj364 Ай бұрын
Better than most paid courses
@Ravi-ik6vt Ай бұрын
I will be installing after sometime hope it works 🙂🥲
@Ravi-ik6vt Ай бұрын
I was trying to install ml agents since 2 days finally found new video
@SihatAfnan-y6o Ай бұрын
Great tutorial. I have a question. Can we read the bounding box coordinates of all the objects that were specified while scene setup?
@LudicWorlds Ай бұрын
Thank you! 🙏 I would expect all the items of furniture to have a bounding box at least - I have not tested every item however.
@451tintan 2 ай бұрын
thank you for going in depth on this
@monsterbai5364 2 ай бұрын
Hi many thanks to the tutorial, can you also give a tutorial about the new meshing feature?
@pandora445 2 ай бұрын
thx!!!!
@tobi6758 2 ай бұрын
Will the XR simulator work too?
@emmanouildrivas4961 2 ай бұрын
Hi, good introduction video. I was thinking maybe you can create a tutorial how to use unity sentis to create an AI NPCs that generate dialogs based on its knowledge database? I saw a video for the Inworld AI kzbin.info/www/bejne/nYamkpuGiKaoqpY but right now it don't exist in the asset store so I was wondering maybe I can create an AI with similar abilities but using instead the Unity Sentis. What do you think about it? Also is there a tutorial how to create models for Unity sentis?
@LudicWorlds 2 ай бұрын
Thanks for the suggestion! I've just checked the 'Inworld' website. and it seems they've changed their licensing - no more free tier! :( I do, in fact, plan to expand upon this tutorial: I would like to feed the results from 'Whisper' into a locally running LLM. Probably would not feasibly to run this on a standalone headset, but it may be OK for PC-based VR.
@gamermixer7953 19 күн бұрын
@@LudicWorlds I tried running a local quantized 2B/1.5B parameter models, and yeah, it didn’t go well. The tracking system, along with the huge background tasks, is always overloading the CPU. There is simply not enough room for an LLM (tested on a Pico 4 with XR2 Gen 1) at least at the moment.
@LudicWorlds 18 күн бұрын
@@gamermixer7953 Yep, I was expecting that the Quest would struggle with even the Tiny Model - but I was keen to try it out regardless. ;) Give it a couple generations though...
@saahil8096 3 ай бұрын
followed tutorial but my AR is not working. It only shows the solid background color. AR session is in along with the ar camera manager too
@motouman3240 3 ай бұрын
Great video and very much to the point. I want to use hand interaction instead of controllers. What do I need to do to enable it?
@bilqinm 3 ай бұрын
does this work with pico 4 ?
@LudicWorlds 3 ай бұрын
I don't own a Pico 4, unfortunately, so I can't advise on what modifications would be needed to make this series compatible with the headset.
@홍성찬-j3q 3 ай бұрын
"I'm curious, are the models that can be run on Unity Sentis limited?"
@LudicWorlds 3 ай бұрын
AFAIK, the models you can run on Unity Sentis are somewhat limited. It's designed to work on-device within your Unity app, so it's best suited for smaller, optimized models. You need to consider the capabilities of your target platform. You can use models exported to the ONNX format, but more complex models might not run efficiently.
@홍성찬-j3q 3 ай бұрын
@@LudicWorlds I wanted to put in a TTS model specialized for Korean and wondered if it was possible! thank you!
@andru5054 3 ай бұрын
thanks for the video