def ValueIteration_Rtest(): VI = ValueIteration(0.00000000001, 0.5, "R") VI.valueIteration(0.00000000001, 0.5) for i in range(10): print(VI.trial_run())
def VI_R_reset(): VI = ValueIteration(0.00000000001, 0.5, "R", restart=True) VI.valueIteration(0.00000000001, 0.5) for i in range(10): print(VI.trial_run())