New answers tagged

0

This is how I see it: The state that a purely reactive agent is reacting to is, in fact, a subset of the set of all possible runs that end with a state. So in theory, E (some state) is a subset of R (finite set of all possible runs with a state as the last element). Standard and purely reactive agents are similar in the sense that the agents' purpose is to ...


1

This is mostly an implementation architecture problem, and the thing is that basically you can implement anything in the traditional setting. To do so instead of having Env<->Agent1<->Agent2, you should have Agent1<->SuperEnv<->Agent2 where SuperEnv contains Env, and simply uses the reward given to SuperEnv by Agent1 and passes it to ...


Top 50 recent answers are included