Figure 9
(a) A part of Fig. 7(a): The difference between the PS agent’s performance approximation, which is given by Eq. (10), and numerical simulations for n = 2. (b) The asymptotic average reward \({ {\mathcal E} }_{\infty }(n,K)\) for the neverending-color scenario (see Eq. 13), as a function of K, the number of categories, for n = 2, 210.
