Table 35: Activity trace of a rudimentary interactionally motivated regulartity learning agent.
Enacted e1r2,1 0: PLEASED Enacted e1r1,-1 learn e1r2e1r1 1: PAINED Enacted e1r1,-1 learn e1r1e1r1 2: PAINED afforded e1r1,-1 Enacted e2r2,1 learn e1r1e2r2 3: PLEASED Enacted e1r2,1 learn e2r2e1r2 4: PLEASED afforded e1r1,-1 Enacted e2r2,1 learn e1r2e2r2 5: PLEASED
Your activity, for Lesson 3, is to understand the trace in Table 35. On Cycle 0, why did the agent choose e1? Why did it receive r2? On Cycle 1, why did it choose e1 again? Why did it receive r1? On Cycle 3, why did it choose e2 and received r2? What will the agent do after cycle 5, and what will be its mood?
See public discussions about this page or start a new discussion by clicking on the Google+ Share button. Please type the #IDEALMOOC035 hashtag in your post: