a tiny bit of innateness, visualizedhttps://twitter.com/daniel_a_berg/status/1222209305690046464 …
-
-
Great work on learning spatial configurations by association, with direct application to robot’s navigation. How do you handle the detection of non-reachable goals? Would this approach help in dealing with combinations of navigation and problem solving as in Sokoban scenarios?
-
reachability analysis a static setting is easy via message-passing. Just propagate forward from the current state until you hit the target or exceed the graph diameter. Sokoban settings can be arbitrarily hard because you can move blocks out of the way etc.
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.