Friday, September 30, 2005

embodied imprinting

these last two days i have been trying to work on the embodied imprinting task.. but the complete task that i want seems a bit too hard to tackle from scratch so i've started a very slow incremental approach by trying simpler tasks so as to validate any small details of the simulation...

1. can the agent distinguish between two circles of different sizes? yes... this was relatively easy.
2. what's the smallest difference that it can evolve to distinguish? it seems like for a 4 inter-node CTRNN a radius size difference of 1 was the smallest it could evolve to discriminate.
3. can an agent catch circles one after the other? this would be needed for my task. also relatively easy.
4. can an agent catch circles of size A and avoid circles of size B when presented one after the other in different orders? this was a bit harder.. and got me to solve a couple of bugs but does work.

the things i've learned so far from this start are:
a) perfect symmetry helps a great amount in this symmetric task... will stick with it for the moment.
b) noise and perhaps more importantly inertia are helping break the symmetry in those undesirable cases,
c) i can see that getting the full task to work won't be easy..

on a different note, aisha, alex and chrisantha submitted their theses today.. i think ian
must have as well..


At 6:40 pm, Blogger eduardo said...

i've just had quite a useful meeting with my supervisor about the projects that i am carying on.. particular interests with regards to the learning scenario inspired on bird imprinting... his main suggestions were with regards to applying a zen approach. which i am going to narrow down to giving the agent more random training examples with less engineered-weighted fitness functions, also to do with biasing the evolutionary search as little as possible with my ill understanding of what the evolved mechanism should be that solves the task. i agree with him 100%.


Post a Comment

<< Home