We spent some time at the recent Embodied Minds Summit at UCLA discussing the need for 'self' in modelling decision processes.
But further work is needed to include rules/goals/rewards which are interoceptively driven
In other words, for AI learning the self also needs a body!
out now in Psych Review, a project many years in the making:
"Reverse Engineering the Centered Self"
bit.ly/4wp9fgN
