Implement a passive learning agent in a simple environment, such as the 4 × 3 world. For the case of an initially unknown environment model, compare the learning performance of the direct utility estimation, TD, and ADP algorithms. Do the comparison for the optimal policy and for several random policies. For which do the utility estimates converge faster? What happens when the size of the environment is increased? (Try environments with and without obstacles.)

Who is better at multi-tasking? in business, employees are often asked to perform a complex task when their atten-tion is divided (i. e., multi-tasking). human factors (may 2014) published a study designed to determine whether video game players are better than non–video game play-ers at multi-tasking. each in a sample of 60 college stu-dents was classified as a video game player or a non-player. participants entered a street crossing simulator and were asked to cross a busy street at an unsigned intersec-tion. the simulator was designed to have cars traveling at various high rates of speed in both directions. during the crossing, the students also performed a memory task as a distraction. two variables were measured for each student: (1) a street crossing performance score (measured out of 100 points) and (2) a memory task score (measured out of 20 points). the researchers found no differences in either the street crossing performance or memory task score of video game players and non-gamers. “these results,” say the researchers, “suggest that action video game players [and non-gamers] are equally susceptible to the costs of dividing attention in a complex task”