How to use Machine Learning AI in Unity! (ML-Agents)

Video quality	The size	Download

Information How to use Machine Learning AI in Unity! (ML-Agents)

Title	:	How to use Machine Learning AI in Unity! (ML-Agents)
Lasting	:	44.51
Date of publication	:
Views	:	373 rb

Great video! Im wondering what extensions you use for vscode to have things like autocomplete
Comment from : Whopper

hello! nice tutorial as always but I have a question It is possible to continue to train the agent in a build environment? I want use it in my game to the players have a personalized experience, so the agent should learn how each player plays the game tks in advance
Comment from : Alex Bilesck

Great video, thank you Mr Code Monkey
Comment from : Ziberian

Hello, i am not getting float values in console when using the ContinuousActions[0] Just getting Zero every time please help me
Comment from : Sani Zahra

i have a problem mlagents-learn dont go
Comment from : Juanecraft 092

Bro I litterally cant complete it because the docs for installation are not working
Comment from : BizzaB

For anyone having problems with trying to run `mlagents-learn`, it helps quite significantly if you be VERY mindful that you install the exact same versions
Comment from : Crafty Does Everything

Really nice video ! I have an idee : The same scenario with an other Agent (agent2) If Agent2 touch agent1, he win
Comment from : Smocrate

good video
Comment from : CS Nim

Wow thanks for this
Comment from : Kalmar-I

please make a video on "How to implement multiagent from scratch?" with mlagents toolkit
Comment from : devanshu singh

which version of python is being used here?
Comment from : WindGod

I'm too dumb for this I tried to follow it all the way but I can't deal with all those errors and hickups constantly, I'll just wait for ML sandboxes to get good GUIs cause all this Python/pip/C#/Unity making my brain hurt
Comment from : Ubister

and even if it did work it wont for long
Comment from : AnyGameAtAll

dosent work as usual
Comment from : AnyGameAtAll

its back to watching other people achieve my dream
Comment from : AnyGameAtAll

Nothing is working and i cant find a different video tutorial that is actually up to date
Comment from : AnyGameAtAll

I know this video is from 2years ago but pls help me When I want to write the "OnCollisionEnter" ( 24:40), I dont get the suggestion and it doesnt work :/ My game is in 2d can this be the problem??
Comment from : staf

if it doesn´t work on 2023, add a rigid body to the blue cube
Comment from : Un MecaNiko

After a few days of following your tutorial little by little (sorry I'm still a newbie),, finally I can understand what you teach, even though there are many changes to the ML-Agents but thank you so much Mrhugo for the knowledge this is very useful for me curious about machine learning
Comment from : Mr Ri

Would love another tutorial to Machine Learning in unity
Comment from : BossAleks123

It didn't work for me :(
Comment from : Egor Pavlovich

I tried this but I failed at multiple things First of all, I couldnt find the unity folder right in C: and I ended up using the one in the appdata oaming folder even though there werent any project files in there Second of all, I placed the virtual environment right in the Unity folder I was running command prompt as administrator aswell And i couldnt download the specific version of pytorch It ended up that i was in my python project without MLagents installed Just like always
Comment from : AnyGameAtAll

Interesting so it's built in to Unity huh
Comment from : Manai

can i do that using a flash drive? and how?
Comment from : potatoes

update the trackcheckpoint script it doesn't have the carcheckpointeventargs, resetcheckpoint and getnextcheckpoint
Comment from : Harris Aamir

Hi Code monkey , what are the alternatives to making an ai , i am trying to make an ai for a card game like gin rummy and will unity machine learning ai give same actions under same moves?
Comment from : pavan venkat

I'm stuck at the part where you need to go to the definition of the agent class, vs just doesn't find it
Comment from : malo Follain

Fantastic tutorial, thank you for all the indepth stepsbrbrQuick question as you mentioned not bothering with CUDA if you don't have an NVIDIA graphics card and it'll just utilize the CPU insteadbrbrFor those of use with AMD cards, do you know if this toolkit integrates with ROCm or OpenCL?
Comment from : H T Spencer

Thanks for a greate tutorial! I've been playing with DL and RL for the last year or so (though not very intesively), and it's one of my main objects of interest, especially RL And it's a greate pleasure to me to finally discover such things as ML-Agents in general, and Unity integration in particular (why didn't I find it before?) Can't even express now what a huge window of possibilites I see now for myself A huge field of experiments I wanted to do for a long time And what an awesome way to create my own environments! I just saw that I can even simply just create the envs in Unity, but make the rest of learning separately in Python!
Comment from : Alexander Egorov

When running mlagents-learn --help I get an traceback error I think something is out of date
Comment from : AlbertSings

It's a very good video but can't make it work , we don't have the same parameters anymore I can't whose between discrete or continuous
Comment from : Sami YAHYA BEY

ờ mây zing gút zóp
Comment from : small family

it says cant build wheel for numpy when i try to install mlagents whats with that?
Comment from : Nerron Lynch

was I supposed to clone repository first?
Comment from : jesse bourassa

Thanks Mr Monkey, I love it man Keep up the great work
Comment from : Fynn HB

Please do the updated video to setup ml agents in unity
Comment from : Ishan

Cool! thank you for the video! It 2 years old but still actual!
Comment from : Inessa De la Frontera

Noob question but here goes, in order to follow along shouldn't we have the same game as you? Do you already have a tutorial for how to make that specific game?
Comment from : Alex Nicolae

Question, great tutorial but I’m a bit stuck, is there a way to make the AI move on a grid and only move in one direction at a time because my one can sometimes go diagonally, but I only want it to move vertically and horizontally I’m trying to make a Snake program brThanks
Comment from : MrHeavyGaming

Does this have any advantage over NavMechAI of unity?
Comment from : Vishnu Teja Koyya

Not sure if this was the case 2 years ago, but there needs to be a rigid body on the cube for the collision to count this took me about an hour to fix Still a Great video thx bro
Comment from : LC

Hey guy…idk if anyone would help with this but…I’m having problems at the part at 3:40 So basically I’m pretty new to working outside of simple code editing for unity…and while tryna instal the venv I get the error returned non zero exit status 1…and the install remains incomplete…pls help…
Comment from : GatoReyd

can you like make it for windows 11?
Comment from : Jak

Doubt!brbrWhen I open tensorboard as stated in this video, Im not getting a graph like the one you get Its simply saying No graph definition files were found
Comment from : L E G E N D

Two and a half years later, MLAgents is still Version 10
Comment from : Tesla Kid

20:00
Comment from : puchikation animation

i just relized there should be another ai thing cald ultra ai that you can have not just normal ai but also any type of aibrepic thing i think
Comment from : sticky the stick figure

Hey, code monkey I did all right but I cant move my ml-agents version is 20, and there don't have space type, there is Continuous Actions and Discrete Actions, i set Continuous Actions 2 and Discrete actions 0, pls help with my problem
Comment from : Koryun Gaboyan

It's too bad Unity has pretty much bailed on this I think the worst thing that happened to Unity was making it public and hiring John Riccitiello They could be so far ahead of the curve by now, now that AI is hotter than a five dollar hooker's door-knob on payday
Comment from : Austice Hayes

Thank you so much for your tutorial for some reason, sometimes the agent falls through the plane, when it hits the wall or the Goal how can i fix this?
Comment from : Hunia Tomoum

My friend thank you very much for this video I always wanted to dive into ML/RL but I always thought the topic is too big With this Unity ML Agents library it's really abstracting away a lot of setup and let's you directly dive into training an AI model Very good explained and introduced!
Comment from : xetra11

I am stuck at around 17:50 ,I keep getting this in my command prompt "[W orchcsrcutils ensor_numpycpp:77] Warning: Failed to initialize NumPy: module compiled against API version 0x10 but this version of numpy is 0xe (function operator ())" And also getting spammed "Heuristic method called but not implemented Returning placeholder actions" in my unity console and receiving 0 in my debuglog Would really appreciate any help from anyone who offers a solution! my guess is maybe something wrong with numpy or maybe just that the ai doesn't have any input and its a new requirement on mlagent, cheers
Comment from : Hamza Sanhoury

I get this error, and I have DecisionRequesterbrbrmlagents_envsexceptionUnityTimeOutException: The Unity environment took too long to respond Make sure that :br The environment does not need user interaction to launchbr The Agents' Behavior Parameters > Behavior Type is set to "Default"br The environment and the Python interface have compatible versionsbr If you're running on a headless server without graphics support, turn off display by either passing --no-graphics option or build your Unity executable as server build
Comment from : j01sonofsleazy

The type or namespace name 'MLAgents' does not exist in the namespace 'Unity' (are you missing an assembly reference?) [Assembly-CS | brbut i have installed it correctly and its showing red line but in unity there is no error but the problem is its not autocorrect my intelesense is not recognizing it please how to fix it
Comment from : AXEL - KNOX

ono again light theme iam burning help !
Comment from : AXEL - KNOX

I'm at the running the batch file part, but it says that "/activate is not recognized as an internal or external command, operable program or batch file" How do I fix this?
Comment from : conder

Doesn't seem that hard
Comment from : David Varga

do you necessarily need nvidia gpu or you can also do ml with other gpu?
Comment from : Rosaria Leone

Hi, I just started learning programming, such a question, according to your code, I made the end of the episode at the moment of collision with the collider, and made the episode restart at the zero coordinate, turned on the collider triggers, but when the game starts, the episode does not restart (and if the collision with the wall, and if with the goal), with what could this be related to?(there don't seem to be any errors in the code, at least VS doesn't complain and Unity doesn't issue errors
Comment from : Miracle

It looks like the most recent version of torch available at the url you provide in the video is 1110 now, so the install process isn't as stright forward as it used to be
Comment from : Nathanael Anderson

Got errors in unity
Comment from : Unknown user

Can I create my own game and env With ml
Comment from : Unknown user

You did a good tutorial only I didnt know where the project came from
Comment from : Unknown user

Where did you get that project from??? Not explained edit I think Ihave it
Comment from : Unknown user

my fps is very low during teaching how do i fix that
Comment from : Throw Off

Another great tutorial thanks for this! I am following and trying to implement in my own game and had a quick question is it possible to reduce the frequency of the Actions? I tried removing the DecisionRequestor script and just calling RequestDecision(); in a less frequent way from my Agent script, but it doesn't seem to work, I still get a huge swathe of Actions right away The issue is in my game that I Tween some shapes into position and its getting overwhelmed with all the requests
Comment from : Spudy Minogues Games

you are an amazing person, just amazing you just saved my final thesis project <3
Comment from : Melih Safa Çelik

Hi, great tutorial, I am a beginner in this field but your video helped me a lot! thanks for thisbrI just have a problem with the collision when testing at 29:16 it seems it can't test the collision, I tried several things like: add Rigidbody to the walls, add a debuglog so I can see if the collision is valid (it isn't), reload the project, try to check the Tags I can't solve this problem, the collision doesn't work and my walls and the goal are "IsTrigger" I know this video is from 2 years ago but if anyone sees this message and knows how to solve it, it would help me a lot!
Comment from : XProKio

Does our game should have predefined movement controls and logic Scripts or it will automatically be implemented from ml agents?brPlease help
Comment from : Atharva Chouhan

i get a problem saying: ERROR: Could not find a version that satisfies the requirement torch (from versions: none) brERROR: No matching distribution found for torch when i try to download pytorch(5:30) does anyone know a fix?bredit: i fixed it but now i cant install mlagents i get error saying: option --use-feature: invalid choice: '2020-resolver' (choose from 'fast-deps', 'truststore', 'no-binary-enable-wheel-cache')bredit 2: it works
Comment from : Rytro

I dont know what is going wrong, every time i press play in the editor i get this error: Could not infer dtype of numpyfloat32brbrI cant fix it
Comment from : Jesper Iwan Jorgensen

For that thing you do at 17:41, it said I won't recognize when I type in mlagents-learn amd how do I get in the virtual environment at that part?
Comment from : GirlyGameDevGamerGirl

I am getting this error when running mlagents-learn "mlagentstrainersexceptionUnityTrainerException: Previous data from this run ID was found Either specify a new run ID, use --resume to resume this run, or use the --force parameter to overwrite existing data"
Comment from : Adeel Bashir

1 I installed package with unity package managerbr2 I see it in packages folderbr3 I copy-paste prefabs from package to my scenebrBut I cant write custom script bcs I cant inherit Agent class?
Comment from : Andrej Urbanek

Followed along this tutorial and was able to train my first agent Great tutorial and attention to details Thanks!
Comment from : OrangeBoyAdventures

Ok, so i started the learning process but it stops around the 500 000th steps and refuse to continue furtherbrbrEdit : I think i found why, it's the max steps process that is locked at 500 000
Comment from : YAY Xikuryas

HOW DO I GET ML AGENTS!!!!!
Comment from : OPBA

Hi, i am getting an Error "ValueError: 'behavioral_cloning' is not a valid RewardSignalType"
Comment from : sreekanth s

Getting "Couldn't connect to trainer on port 5004 " error, trying to learn stuff with unity since the morning and this is like the 10th or 11th errors Im getting
Comment from : Zegg XR

I can't find the pytorch version
Comment from : Jayme McNair

How do I "export" the behavior so that it can be used without running python?
Comment from : Elias Willerup

Great video, thank you, I did want to mention I had to downgrade to the python version you were using in order for it to work, I am sure there is an updated way but I could not figure it out Also for anyone using the sample packs from Unity's github pushblock with input was broken and I had to remove that out of the folder for there to be no complication errors
Comment from : Tony T

Hi this is great video But I have some issues on my unity console says: couldn't connect to trainer on port 5004 using API version 150 will perform inference instead
Comment from : Nana Peprah Samuel