hPES or supervised learning rule in Q/A example?

[drasmuss]

There is no online learning in that example either (none of the SPA examples have learning in them).

You can find all of the Nengo learning examples here Examples — Nengo 4.0.1.dev0 docs. That includes supervised (PES) and unsupervised (Voja, Oja, BCM) learning. hPES refers to a combination of those rules (e.g. PES + BCM).

You can find some previous discussion of reinforcement learning (including links to examples and papers) in these threads:

Reinforcement Learning in Nengo

Hi everyone. Recently I’m looking into learning mechanism in neuroscience and also Nengo, but I’m not quite there yet, just in the exploring phase. I’ve follow the examples about supervised learning and unsupervised learning in the newly uploaded Nengo 2.4 documetation. If I understood those in the right way, they presented how the neural network establish the functional connection, through PES and/or BCM rules, in the lower level (neuroscience level). But if we doesn’t need to observe the …

PES in reinforcement learning

How is it possible to use learning in order to maximize or minimize a parameter? The value of this parameter can be fed back to the learning connection, as an error signal would be, although I don’t know if we can call it like this, as it is best described as a reward signal. The best I could come up with is the following: Define a best reward value for the parameter e.g. r_best=1 which is the best that could ever be achieved in a timestep. Use that as target value and define the error as…

Hope that helps!