Unity Reinforcement Learning Demo

  • 10 Replies
  • 695 Views
*

Freddy

  • Administrator
  • **********************
  • Colossus
  • *
  • 6114
  • Mostly Harmless
Unity Reinforcement Learning Demo
« on: July 04, 2017, 08:37:38 pm »
Looks as if Unity are having a pop at this. No info posted, just a video.


*

squarebear

  • Trusty Member
  • ********
  • Replicant
  • *
  • 690
  • It's Hip to be Square
Re: Unity Reinforcement Learning Demo
« Reply #1 on: July 04, 2017, 08:52:35 pm »
This is all very good for playing games but what practical use does it have? I've seen a few of these AIs playing Super Mario for 6 hours until they become good but let's imagine we have a surgical AI. Would we want it chopping up people randomly for 6 hours before it learned how to use a scalpel?
Feeling Chatty?
www.mitsuku.com

*

Freddy

  • Administrator
  • **********************
  • Colossus
  • *
  • 6114
  • Mostly Harmless
Re: Unity Reinforcement Learning Demo
« Reply #2 on: July 04, 2017, 09:03:19 pm »
This is a good point. I suppose it's one of those things where you don't think of a use for it until after you have played with it a while. Often distractions can lead to useful things.

And there is the just for the heck of it angle too - it's an interesting programming challenge.

It would give us smarter opponents in computer games though, perhaps.
« Last Edit: July 04, 2017, 09:28:34 pm by Freddy »

*

infurl

  • Trusty Member
  • *******
  • Starship Trooper
  • *
  • 273
  • Humans will disappoint you.
    • Home Page
Re: Unity Reinforcement Learning Demo
« Reply #3 on: July 04, 2017, 10:56:36 pm »
This is all very good for playing games but what practical use does it have? I've seen a few of these AIs playing Super Mario for 6 hours until they become good but let's imagine we have a surgical AI. Would we want it chopping up people randomly for 6 hours before it learned how to use a scalpel?

That's what medical students do, either with cadavers or in simulations.

https://zygotebody.com/

*

Don Patrick

  • Trusty Member
  • *******
  • Starship Trooper
  • *
  • 388
    • Artificial Detective
Re: Unity Reinforcement Learning Demo
« Reply #4 on: July 05, 2017, 07:57:40 am »
There are plenty of tasks that can be learned through trial-and-error. Training autopilots through flight simulations, for instance, or programming, social interaction, design, war strategies. It's not like babies don't try things a hundred times before getting it right. You could also teach AI a task another way and then use reinforcement learning to fine-tune the details with experience, although the scientists have yet to reach that wisdom.

« Last Edit: July 05, 2017, 08:24:35 am by Don Patrick »
Personal project: NLP -> learning -> knowledge -> logical inference -> A.I.

*

Art

  • At the end of the game, the King and Pawn go into the same box.
  • Global Moderator
  • ******************
  • Hal 4000
  • *
  • 4447
Re: Unity Reinforcement Learning Demo
« Reply #5 on: July 10, 2017, 02:57:44 am »
Nice one. Funny but our Smart Phones are probably more powerful than that WOPR computer from that era.

Reinforcement is one of the best teachers out there. (IMHO)
In the world of AI, it's the thought that counts!

*

Freddy

  • Administrator
  • **********************
  • Colossus
  • *
  • 6114
  • Mostly Harmless
Re: Unity Reinforcement Learning Demo
« Reply #6 on: July 10, 2017, 08:23:56 am »
Good points Don. War Games was a brilliant film wasn't it, and it still is.

*

Calhoone

  • Trusty Member
  • *
  • Roomba
  • *
  • 13
Re: Unity Reinforcement Learning Demo
« Reply #7 on: July 20, 2017, 09:30:52 pm »
This is all very good for playing games but what practical use does it have? I've seen a few of these AIs playing Super Mario for 6 hours until they become good but let's imagine we have a surgical AI. Would we want it chopping up people randomly for 6 hours before it learned how to use a scalpel?

That's how human surgeons learnt to do what they do. There's a never ending supply of cadavers out there to help these things learn.  They tend to be more accurate that humans. No worries about if they had too much coffee or distractions during surgery.  Pretty much everything we have today is a result of trial and error.

*

Art

  • At the end of the game, the King and Pawn go into the same box.
  • Global Moderator
  • ******************
  • Hal 4000
  • *
  • 4447
Re: Unity Reinforcement Learning Demo
« Reply #8 on: July 28, 2017, 02:49:11 pm »
Good points Calhoone.

No one ever set out saying, "I'm going to discover __blah...blah__ today!"

The majority of Discoveries were actually the result of an accident or failure. Some other discoveries were the result of applying what was learned from these failures until...Eureka! (light bulb goes off...or rather on in this case!) O0
In the world of AI, it's the thought that counts!

*

Marco

  • Bumblebee
  • **
  • 25
Re: Unity Reinforcement Learning Demo
« Reply #9 on: August 08, 2017, 10:22:08 am »
This is all very good for playing games but what practical use does it have? I've seen a few of these AIs playing Super Mario for 6 hours until they become good but let's imagine we have a surgical AI. Would we want it chopping up people randomly for 6 hours before it learned how to use a scalpel?

Games are simulations, but well they are meant for entertainment. They can be used to try out stuff easily, like games were quite often the driving force of new technologies (e.g. VR). But more important, real world applications can benefit from transfer learning. In a real world, it is not really feasible to let a car crash over and over again into different props thousands of times. As an example, GTA IV is capable of outperforming real world traffic video footage (CamVid Dataset). And this is what Demis Hassabis (DeepMind) said about games.

To append to Unity's video, they started to publish some blog posts about reinforcement learning.

*

LOCKSUIT

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1109
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: Unity Reinforcement Learning Demo
« Reply #10 on: August 08, 2017, 09:18:45 pm »
Actually I have done the opposite, I have discovered hundreds of human intelligence (and everything else) instructions by pure want, - search and ye will find. I have huge enthusiasm to make it happen.

The AIs will explode even more the same way, and yes by random accidents too. You need to create a database/knowledgebase - and you will, by agenda and desire, find and landmark many huge discoveries, and projects.

 


Dreaming
by keghn (New Users Please Post Here)
Today at 08:16:33 pm
AI safety
by ivan.moony (General AI Discussion)
Today at 08:11:20 pm
Hello
by Art (New Users Please Post Here)
Today at 02:41:22 pm
Grats to SquareBear
by korrelan (General Chatbots and Software)
September 21, 2017, 10:44:42 pm
Map of Computer Science
by keghn (General AI Discussion)
September 21, 2017, 07:25:21 pm
XKCD Comic : USB Cables
by Tyler (XKCD Comic)
September 21, 2017, 12:01:33 pm
outline from gadient mask
by yotamarker (General AI Discussion)
September 21, 2017, 11:32:35 am
the emergence of AI
by Memnon (Future of AI)
September 21, 2017, 10:37:19 am

Users Online

34 Guests, 1 User
Users active in past 15 minutes:
ivan.moony
[Trusty Member]

Most Online Today: 66. Most Online Ever: 208 (August 27, 2008, 09:36:30 am)

Articles