![]() |
ComputeAlpha_aPURPOSE
Compute the alpha_i_n-element for the given action and belief.
SYNOPSIS
function Element_a=ComputeAlpha_a(P,V,b,a,Alphas_j_a_o)
DESCRIPTION
Compute the alpha_i_n-element for the given action and belief. Define the alpha-elements to be used in the backup (The \alpha_n^i elements). The defintion of this function is given in abstract way (without regard of the type of the underlying state space using an abstract expectation operator) in Section 3.1 equation (8). CROSS-REFERENCE INFORMATION
This function calls:
SOURCE CODE
0001 function Element_a=ComputeAlpha_a(P,V,b,a,Alphas_j_a_o) 0002 % Compute the alpha_i_n-element for the given action and belief. 0003 % 0004 % Define the alpha-elements to be used in the backup (The \alpha_n^i 0005 % elements). 0006 % 0007 % The defintion of this function is given in abstract way (without regard 0008 % of the type of the underlying state space using an abstract expectation 0009 % operator) in Section 3.1 equation (8). 0010 0011 rj=num2cell(1:size(V)); 0012 O=get(P,'ObsSpace'); 0013 gamma=get(P,'gamma'); 0014 no=dim(O); 0015 Element_a=GetRewardModelFixedA(P,a); 0016 for o=1:no 0017 if isempty(Alphas_j_a_o) 0018 Elements_j=cellfun(@(j)(ComputeAlpha_j_a_o(P,V,j,a,o)),rj,'UniformOutput',false); 0019 else 0020 Elements_j=Alphas_j_a_o(:,a,o); 0021 end 0022 [v_a_o nAlpha_j]=max(cellfun(@(g)(Expectation(b,g)),Elements_j)); 0023 Element_a=Element_a+gamma*Elements_j{nAlpha_j}; 0024 end 0025 0026 0027 |