I see a lot of stuff arguing we need embodiment.

I don’t think this is the most urgent task. For me the most urgent task is creating machines that model the , and can query these for a variety of tasks, integrating a rich apparatus for understanding the with a rich behavioural repertoire, combining understanding of the environment with skill in an organic way . The recent paper on imagination augmented networks for example was a good use of this approach. Effectively moving out of a behaviorist approach to reinforcement , towards something that utilizes sophisticated internal architectures and models the processes and relationships in its environment.

To make things confusing though, some people refer to the account I sketched out above as ’embodiment’, which makes me wonder if the term isn’t losing its meaning.

Source link


Please enter your comment!
Please enter your name here