Chapter 12

Offline lambda-return

source("./offline_lambda_return_random_walk.R")

Figure 12.3: Performance of the off-line lambda-return algorithm on 19-state Random walk

plot_fig12.3()

TD(lambda) and true online TD(lambda)

source("./TD_lambda_true_online_TD_lambda_random_walk.R")

Figure 12.6: Performance of TD(lambda) algorithm on 19-state Random walk

plot_fig12.6()

Figure 12.8: Performance of online lambda-return algorithm on 19-state Random walk

plot_fig12.8()

Sarsa(lambda)

source("./sarsa_lambda_mountain_car.R")

Figure 12.10: Early performance on the Mountain Car task of Sarsa(lambda)

plot_fig12.10()

Figure 12.11: Summary comparison of Sarsa(lambda) algorithms on Mountain Car

plot_fig12.11()