Robots Evolve and Learn to Lie

Status
Not open for further replies.

Mo0o

Lifer
Jul 31, 2001
24,227
3
76
http://discovermagazine.com/20...e-and-learn-how-to-lie

80. Robots Evolve And Learn How to Lie
01.14.2008
by Michael Abrams

Robots can evolve to communicate with each other, to help, and even to deceive each other, according to Dario Floreano of the Laboratory of Intelligent Systems at the Swiss Federal Institute of Technology.

Floreano and his colleagues outfitted robots with light sensors, rings of blue light, and wheels and placed them in habitats furnished with glowing ?food sources? and patches of ?poison? that recharged or drained their batteries. Their neural circuitry was programmed with just 30 ?genes,? elements of software code that determined how much they sensed light and how they responded when they did. The robots were initially programmed both to light up randomly and to move randomly when they sensed light.

To create the next generation of robots, Floreano recombined the genes of those that proved fittest?those that had managed to get the biggest charge out of the food source.

The resulting code (with a little mutation added in the form of a random change) was downloaded into the robots to make what were, in essence, offspring. Then they were released into their artificial habitat. ?We set up a situation common in nature?foraging with uncertainty,? Floreano says. ?You have to find food, but you don?t know what food is; if you eat poison, you die.? Four different types of colonies of robots were allowed to eat, reproduce, and expire.

By the 50th generation, the robots had learned to communicate?lighting up, in three out of four colonies, to alert the others when they?d found food or poison. The fourth colony sometimes evolved ?cheater? robots instead, which would light up to tell the others that the poison was food, while they themselves rolled over to the food source and chowed down without emitting so much as a blink.

Some robots, though, were veritable heroes. They signaled danger and died to save other robots. ?Sometimes,? Floreano says, ?you see that in nature?an animal that emits a cry when it sees a predator; it gets eaten, and the others get away?but I never expected to see this in robots.?
 
S

SlitheryDee

Someone needs to assassinate that guy before this gets out of hand.
 

TraumaRN

Diamond Member
Jun 5, 2005
6,893
63
91
creepy.....but cool. And no need to assassinate him, I'm sure one of the robots will take care of him..
 

Cogman

Lifer
Sep 19, 2000
10,286
147
106
Welcome to last year. Robots have evolved immensely since then. Most of them are now posting on ATOT even as we speak.
 

nublikescake

Senior member
Jul 23, 2008
890
0
0
I'll be the pessimist here and say that it could just be a glitch in the programming of the robots. When the "cheater" robots "deceptively" eat the food that they warned others not to eat, it could be that they sent out the warning to the others due to a programming glitch since the food was safe to eat after all and they ate it.
 

YOyoYOhowsDAjello

Moderator<br>A/V & Home Theater<br>Elite member
Aug 6, 2001
31,205
45
91
I read through the article briefly
http://www.cell.com/current-bi...28-1?large_figure=true

Video
http://download.cell.com/curre...0982207009281.mmc2.mov

There were two types of communication systems in the colonies, those that were based on signaling when at food and those based on signaling when at or near poison.

The only part of the article that seemed to address any sort of deception was this:

"The only treatment where the possibility to communicate did not translate into a higher foraging efficiency was when colonies comprised low-relatedness robots subjected to individual-level selection (Figure4D). In this case, the ability to signal resulted in a deceptive signaling strategy associated with a significant decrease in colony performance compared to the situation where robots could not emit blue light. An analysis of individual behaviors revealed that in all replicates, robots tended to emit blue light when far away from the food. However, contrary to what one would expect, the robots still tended to be attracted rather than repelled by blue light (17 out of 20 replicates, binomial-test z score: 3.13, p < 0.01). A potential explanation for this surprising finding is that in an early stage of selection, robots randomly produced blue light, and this resulted in robots being selected to be attracted by blue light because blue light emission was greater near food where robots aggregated. Indeed, in another set of experiments (data not shown) we found that, when constrained to produce light randomly, robots were attracted by blue light because the greater level of blue light emission associated with the greater density of robots near food provided a useful cue about food location. Emission of light far from the food would then have evolved as a deceptive strategy for decreasing competition near the food. Consistent with this view, the tendency of robots to be attracted by blue light significantly decreased during the last 200 generations (Mann-Whitney test, df = 18, p< 0.05)."
 

nublikescake

Senior member
Jul 23, 2008
890
0
0
Originally posted by: Cogman
Welcome to last year. Robots have evolved immensely since then. Most of them are now posting on ATOT even as we speak.

Shhhhhh!!!! Don't forget the First Rule of Robotics!
 

Gothgar

Lifer
Sep 1, 2004
13,429
1
0
Originally posted by: YOyoYOhowsDAjello
I read through the article briefly
http://www.cell.com/current-bi...28-1?large_figure=true

Video
http://download.cell.com/curre...0982207009281.mmc2.mov

There were two types of communication systems in the colonies, those that were based on signaling when at food and those based on signaling when at or near poison.

The only part of the article that seemed to address any sort of deception was this:

"The only treatment where the possibility to communicate did not translate into a higher foraging efficiency was when colonies comprised low-relatedness robots subjected to individual-level selection (Figure4D). In this case, the ability to signal resulted in a deceptive signaling strategy associated with a significant decrease in colony performance compared to the situation where robots could not emit blue light. An analysis of individual behaviors revealed that in all replicates, robots tended to emit blue light when far away from the food. However, contrary to what one would expect, the robots still tended to be attracted rather than repelled by blue light (17 out of 20 replicates, binomial-test z score: 3.13, p < 0.01). A potential explanation for this surprising finding is that in an early stage of selection, robots randomly produced blue light, and this resulted in robots being selected to be attracted by blue light because blue light emission was greater near food where robots aggregated. Indeed, in another set of experiments (data not shown) we found that, when constrained to produce light randomly, robots were attracted by blue light because the greater level of blue light emission associated with the greater density of robots near food provided a useful cue about food location. Emission of light far from the food would then have evolved as a deceptive strategy for decreasing competition near the food. Consistent with this view, the tendency of robots to be attracted by blue light significantly decreased during the last 200 generations (Mann-Whitney test, df = 18, p< 0.05)."

weird.... it is good to be able to put a mental picture to what they are calling robots

I wasn't sure if these were big or small, those look small, for now :p
 

YOyoYOhowsDAjello

Moderator<br>A/V & Home Theater<br>Elite member
Aug 6, 2001
31,205
45
91
Originally posted by: Gothgar
Originally posted by: YOyoYOhowsDAjello
I read through the article briefly
http://www.cell.com/current-bi...28-1?large_figure=true

Video
http://download.cell.com/curre...0982207009281.mmc2.mov

There were two types of communication systems in the colonies, those that were based on signaling when at food and those based on signaling when at or near poison.

The only part of the article that seemed to address any sort of deception was this:

"The only treatment where the possibility to communicate did not translate into a higher foraging efficiency was when colonies comprised low-relatedness robots subjected to individual-level selection (Figure4D). In this case, the ability to signal resulted in a deceptive signaling strategy associated with a significant decrease in colony performance compared to the situation where robots could not emit blue light. An analysis of individual behaviors revealed that in all replicates, robots tended to emit blue light when far away from the food. However, contrary to what one would expect, the robots still tended to be attracted rather than repelled by blue light (17 out of 20 replicates, binomial-test z score: 3.13, p < 0.01). A potential explanation for this surprising finding is that in an early stage of selection, robots randomly produced blue light, and this resulted in robots being selected to be attracted by blue light because blue light emission was greater near food where robots aggregated. Indeed, in another set of experiments (data not shown) we found that, when constrained to produce light randomly, robots were attracted by blue light because the greater level of blue light emission associated with the greater density of robots near food provided a useful cue about food location. Emission of light far from the food would then have evolved as a deceptive strategy for decreasing competition near the food. Consistent with this view, the tendency of robots to be attracted by blue light significantly decreased during the last 200 generations (Mann-Whitney test, df = 18, p< 0.05)."

weird.... it is good to be able to put a mental picture to what they are calling robots

I wasn't sure if these were big or small, those look small, for now :p

Yeah, most of the experiment was just simulated too. I supposed that's necessary to get 500 generations with many trials ;)

They produced random starting software for the robots (random movement, light blinking, etc.)
They then simulated 500 generations of robots with a simulator. The selection of which robots passed on their software (with "mutations") differed depending on how they were doing the experiment. (Some included lights, some did not... some were based on individual selection and some on colony selection).

After they did the simulation (or I supposed at any point during the simulation), they could upload that latest software for the simulated robots into the "real" robots to confirm that it was accurate.
 
Status
Not open for further replies.