Slashdot Mirror
Evolving Robots Learn To Prey On Each Other
quaith writes "Dario Floreano and Laurent Keller report in PLoS ONE how their robots were able to rapidly evolve complex behaviors such as collision-free movement, homing, predator versus prey strategies, cooperation, and even altruism. A hundred generations of selection controlled by a simple neural network were sufficient to allow robots to evolve these behaviors. Their robots initially exhibited completely uncoordinated behavior, but as they evolved, the robots were able to orientate, escape predators, and even cooperate. The authors point out that this confirms a proposal by Alan Turing who suggested in the 1950s that building machines capable of adaptation and learning would be too difficult for a human designer and could instead be done using an evolutionary process. The robots aren't yet ready to compete in Robot Wars, but they're still pretty impressive."
Minor detail perhaps, but as Academic Editor in Chief of PLoS Biology I want to point out that the paper was in PLoS Biology not PLoS One ...
Definitely an interesting continuation of work being done by various groups over the past couple of decades.
But one thing to note is that crossover isn't especially useful in neural network evolution. In early stages of evolution, it's really no better than random large perturbation of large swaths of the genome. In later stages, it can actually decrease the speed of evolution toward high fitness genomes, because at least some of the time (particularly if there are multiple "species" in the population) crossover ends up being a random large perturbation which hinders the search of local fitness space by mutation; the rest of the time (when individuals from the same "species" are crossed) crossover is no better than mutation.
The reason for this is because the parameters of a neural network are not functional. A section of the genome may correspond to a weight between neurons, but that weight doesn't have a specific function. In biological organisms, each gene is transcribed/translated into a protein, and that protein may have a particular function within the cell. If that gene is acquired by a descendant through crossover, the protein could serve the same (or a somewhat modified) role it served in its parent, even if the rest of the descendant's genome was acquired from the other parent. But with artificial neural networks, the parameters were all evolved as parts of a whole, where each individual parameter has no function on its own, but the behavior emerges from having all of those parameters at the same time.
This could potentially be mitigated by the genome encoding scheme one uses, and of course, if the crossover rate is low enough, the ultimate effect would be small.
The noun "orientation" is derived from the verb "orient", not the other way around.
-- "At Microsoft, quality is job 1.1" -- PC Magazine, Nov. 1994
This kind of behavior was first demonstrated/modeled (AFAIK/IIRC) as part of the Tierra simulations almost twenty years ago. Though I don't have a reference to hand, I know it's been done in neural networks before too.
So other than the 'sizzle' (as opposed to 'steak') of doing it with robots, can anyone explain what is new here?
You don't need physical robots running around a maze to demonstrate AI.
Seastead this.
By not posting dumbass shit like this without first checking the Post Anonymously box.
Noob.
I believe it killed itmself because having a bit of Rose Tyler's DNA within it was too much of an abomination even for it.
Well... ok, technically it killed itself because integrating human DNA caused it to feel human emotions like regret, and it didn't like that one bit.