I uploaded a version of Mat's NEAT program that will compile under Visual Studio 2005. All I did was fix in-loop variable creations (a no- no from 2005 onward)...
Colin, I finally got around to reading through your long post reasoning about speciation techniques. I appreciate the overview of pros and cons of several...
Lancer, thanks for the contribution. Several years ago, Prof. Stephanie Forrest at the University of New Mexico told me about a class assignment she had given...
Hello all- Ever since I first understood HyperNEAT I have wanted to see how it would perform at controlling legged robots. A paper I wrote on that subject was...
Cícero Augusto Bacharel em Ciência da Computação - UFBA Mestrando em Ciência da Computação - UFSC ... "You've achieved success in your field when you...
Jeff, Cool! Thanks for sharing the paper and video's. I've given the paper a quick read, but I really need to spend more time on it. I hope to be able to...
I've been thinking of adding CUDA support to my HyperNEAT implementation. Can you elaborate on the process of porting the code to the GPU? Did you find any...
Hi Jeff. Very interesting paper! :) It reminds me about the experiments I made with HyperNEAT for controlling biped robots. Did you try using leaky-integrator...
... Thanks. I'm glad you enjoyed it. ... I have thought a lot about your biped experiment. I'd be really interested in hearing your opinion, and that of anyone...
Hi Jason, The process of porting the code is an interesting (to me) discussion. The central issue (some might call pitfall) is partitioning for parallel ...
... Hi Ken. Thanks for checking it out. What did you think of the videos? I am interested to see if others agree with my feelings that the HyperNEAT robotic...
Hi Jeff, Thanks for posting the paper, nice work. It's another clear win for HyperNEAT and in an area with commercialisation opportunities I would suggest. ...
Hi Jeff. Here is my opinion about the 4 hypothesis you suggested. ... Definitely true! :) While robots with 3+ legs are generally stable, biped robots have...
Just a random thought I had about evolving biped gaits: Have you considered first evolving a quadruped gait, then switching the fitness function to one that's...
... Thanks Colin. By commercial opportunities, do you mean in the domain of real (not simulated) legged robots? If so, I agree. I'd love to test this out on a...
... Hi Peter. I agree! Bipedalism is much harder. But I suspect that HyperNEAT is up to the task. It'd be cool to get it working. :-) ... Did you ever try the...
Hi all, I thought the following might be of interest to some of you. We recently presented a paper at the IEEE Computational Intelligence and Games 2008...
Hi Georgios, I hope things are well. Thanks for sharing your paper. The problem that rtNEAT requires a high level of interaction indeed constrains the types...
Thanks for the heads up. It has been a very long time since I have messed with any type of AI coding (over a decade) so it will pretty much be like starting...
One method of reducing the number of distance checks is to do a form of space partitioning. Break each space up into much smaller areas and assign each cluster...
Hi Ken, Thanks for the feedback. Hope you are doing well too. RTS games are very particular with respect to real-time learning via neuro-evolution; not only...
I am working at creating a version NEAT in National Instrument's LabView. I am using Buckland's NEAT for Windows code as a convention to follow. It has...
Hey Reymond, I agree with both your points. And I got a little advice for you when using Buckland's NEAT Code. In the Cga::ResetAndKill there is a bug which...
We have actually been running biped evolution experiments recently at UCF because we would like to use it as a test domain in the future as well. In our...
Hi Ken. I agree that the model morphology is critical. When I was playing with my model, I noticed that there is a great difference in performance for even a...
Hi Ken- ... That is exciting that you are working on bipeds. I am anxious to see your results. Since you mention it as a test bed, I am curious to hear what...
... Yes. I'm just thinking broadly of the commercial viability of a cheap leg based locomotion controller. Wheels are of course really good for many situations...
Hi Jeff, From: Jeff Clune <jclune@...> ... Of course you need recurrence. For some theoretical explorations about the dynamics of leaky integrators you can...
... I fully agree with you. I wonder how long it will be before we see such robots carrying gear around for us. Big dog certainly implies that it won't be that...
Having problems with message search?
Fill out this form to ensure your group is one of the first to be migrated to the new message search system.
