A downloadable game for Windows

Download NowName your own price

We have been hard at work on taking our prototype to the next level. The official version of this game is now called Little Learning Machines and you can download the early access version today on our  Steam page! 

DOWNLOAD LITTLE LEARNING MACHINES EARLY ACCESS TODAY!! 🎉

↘️ ⬇️⬇️⬇️ ↙️

WISHLIST HERE

↗️ ⬆️⬆️⬆️ ↖️



If you had the power to decide how A.I. behaves, what would you train it to do? Animo Lab is a simulation game where you can put your A.I. training skills to the test! 

  • Train little robots with a variety of strategic behaviors to accomplish all sorts of actions and challenges in the Animo world.
  • Adjust your robot’s rewards and punishments to improve efficiency. 

But be careful,  A.I. is a very powerful force, and the fate of the world may depend on your choices!

At its core, Animo Lab is revolutionary as it simplifies the complex and time intensive operation of training generalizable characters with reinforcement learning to a process that only take a few minutes to do. Through the methodology of reinforcement learning, these little robots can actually learn from their mistakes and make better decisions throughout the players progression in the game.

Animo Lab is a precursor to Animo which will be releasing later next year.  The full version will include a highly emotive journey where robots can be trained to revitalize and rebuild desolate wastelands into lush habitable environments. Share and trade trained robots with friends and construct environments unique to your robots’ strengths. With multiple robots to choose from, and many different ways to train them, will your robots have what it takes to change the Animo world for the better? By teaming creativity with these budding intelligent actors, the possibilities are endless!

Animo Lab is ideal for...

  • People who want to learn more about Reinforcement Learning and modern A.I. 
  • Educators, parents, researchers and students who are looking for a fun and easy way to make Reinforcement Learning more digestible for kids.
  • Creative and technical minds that enjoy solving problems while also having fun in the process
  • People who like intelligent robots 

Note: The game uses your computer to train real A.I. neural networks. As a result, you may hear your computer fans spin-up faster than usual. Don't be alarmed as this is completely normal. The performance of your computer will determine how quickly your robots can learn. Happy training! 

StatusIn development
PlatformsWindows
Rating
Rated 4.6 out of 5 stars
(5 total ratings)
Authortransformsai
GenreEducational, Simulation, Strategy
Made withUnity
Tags3D, artificial-intelligence, Automation, Experimental, Exploration, Open World, Robots, Sandbox
Average sessionA few hours
LanguagesEnglish
InputsKeyboard, Mouse
AccessibilityInteractive tutorial
LinksTwitter/X

Download

Download NowName your own price

Click download now to get access to the following files:

Animo Lab_Windows_2.0.1_RC3.zip 50 MB

Development log

Comments

Log in with itch.io to leave a comment.

(+1)

Seems like a cool game however, i don't  buy from  Steam. However  if the full version is ever here you  made a sale. 

(+1)

im the exact opposite. i only buy on steam and never on itch. you should download steam because they have great features and are doing virus checks and testing before each game is released to the public. on itch there are a lot of games that contain malicious code in them.

(+2)

I buy from GOG,  Itch.io  and off of developers website through  Humble Bundle my current  living situation  along with Steam's lack of support  is a pass for me . I have never had trouble  with viruses on itch.io  but I definitely understand.  I'm at The point  that if a game  isn't  available on a platform I shop at they obviously are  doing  so well they don't  need my money.

Hey! Thanks for checking out our prototype :) As of right now, the full version of Little Learning Machines is only available on Steam! Will reply here if we decide to change that in the future!

cool project but stuck on tutorial. why would you make it so hard without actual hints or aynthing? im particularly stuck on juggler.

(+1)

hi , i keep being stuck on the loading screen , even if there's nothing left to install :/

Deleted 2 years ago

try again

it is not working

(1 edit)

get the right version or try again, even more, it took me like 6 tries to get it working

(+1)

stuck on the loading screen...

I just got it, how long does it check installation?

Usually a minute or so.... If it takes longer, try deleting it and re-downloading it

Hi there, thank you for the download! 
Installing ml-agents for the first time may take a bit longer. However once it's complete, it should not take more than a few seconds to check installation. Please contact us at accounts@transforms.ai if the issue persists. Thanks and happy training!

Very notable

this is soo cool!

i am just sometimes stuck in the menus! I really love it though. Wish you continue working on it!:)

Thank you for downloading the game and giving it a try! We do plan to continue working on it. We are looking for play testers for our next release. If you're interested, send us an email at accounts@transforms.ai -  Cheers! 

doesnt have a start button anywhere

(-1)

I am a 3d modeler and I would like to talk to you, could you give me an email or preferably some other way to communicate with you?

Recommend contacting them through their website:

https://transforms.ai/contact

Hi! we're def looking for some help! As zappybiby said below, you can reach us on our site. :)

Hello, nice to meet you, try to communicate with me, but I do not understand how your page works, could you give me an email or the means that suits you, for this post, I would appreciate it

Very intuitive and a great tool to introduce someone to reinforcement learning. Excited to play the full version of this when released!

Feedback:

  1. Show volume settings during tutorial - I had to quickly skip the tutorial because the narrator was too loud and there wasn't a way to adjust volume in-game. 
  2. In training mode the bot will sometimes 'spit' out a ball into the air - I wasn't sure what this is supposed to indicate.
  3.  Include a way to reset a bot's brain to forget all prior training. Also, as a suggestion, maybe the best performing brain (maximum 'love' / minimum 'fear') could be saved so you can revert to it. Right now the last 10 brains are saved but it'd be nice if a brain could be protected from being overwritten - something I've seen in other reinforcement learning games like boxcar2d.

Bugs:

  1. The 'reset world' button stopped working after the first session - after re-opening the game, clicking it doesn't do anything and the bots that died don't respawn. This persists despite restarting the game. 
  2. The 'raise' and 'lower' tools in training mode can be brought into the overworld by having them selected in training mode and then clicking 'return to overworld'.
  3. I have repeatedly encountered a bug where when I click on the overworld it teleports a bot/item to where my cursor is. I believe this issue is related to #2 (maybe I had a bot/item selected in training and it carried over) but I can't reproduce it consistently. 

Whoa! thank you for the feedback.

Some responses:

Feedback:
1) Great point! I was once also jumpscared by my colleague's voice. There is a narration button that disables the voice over. Volume controls may come in the final version.
2) That's a new brain! I'll let our artist know that it looks like spitting. 
3) I love that idea! We were looking to do something like that, but we were trying to balance complexity and usability. We'll think about it for the next version.

Bugs:
1,2, and 3 seem to be the same issue! (Shakes fist at state machines) thank you so much for capturing it. We'll try to get a new verision out with the fix asap :)

Conclusion:

Thank you so much for playing this game!!! And thank you for the feedback! We're so happy that you liked it. :)

goood game nice to play continue making games developer okay

Thank you for the feedback!

no welcome