/*! Returns the action that maximizes the Q-value for the given state
*
*/
size_t argmax_q(const mat & Q, const size_t &state, const uvec & possible_a){
// There might be several actions that give the max Q-value
vector<size_t> maxq_actions;
// Calculate the max Q-value for this state and actions possible from here
double maxq = Q(state, possible_a(0));
for(auto i : range(1,possible_a.size())){
if(Q(state,possible_a(i)) > maxq){
maxq = Q(state,possible_a(i));
}
}
// Check if there are several actions with same q-value as maxq
for(auto i : range(possible_a.size())){
if (Q(state,possible_a(i)) == maxq){
maxq_actions.push_back(possible_a(i));
}
}
// Return the single action that maximizes the Q-value or
// randomly one of the actions that maximize the Q-value.
if(maxq_actions.size() > 1){
return maxq_actions[randint(maxq_actions.size())];
}else{
return maxq_actions[0];
}
}
/*! Combinations of integer ranges
*
* Calculates all combinations of integer ranges of which the length is given in the input vector.
*
* @param dim vector of dimensions for each variable
*
* @retval Matrix of size (prod(dim) x #variables)
*/
Mat<size_t> combinations(const uvec & dim){
size_t nvariables = dim.size();
size_t ncombinations = prod(dim);
Mat<size_t> result(ncombinations, nvariables);
for(auto var_i : range(nvariables)){
size_t var_val = 0;
size_t var_len;
if (var_i == nvariables-1){
var_len = 1; // Last variable
}else{
var_len = prod(dim(span(var_i+1,nvariables-1)));
}
for(auto j : range(ncombinations)){
if ((j % (var_len * dim(var_i)) == 0) && j > 0){
var_val = 0;
}else if ((j % var_len == 0) && j > 0){
var_val += 1;
}
result(j, var_i) = var_val;
}
}
return result;
};
// Set difference
// - Return vector Ea with elements of Ec removed
// ======================================================================
uvec setdifference(uvec Ea, uvec Ec){
int na = Ea.size();
for(int j=na; j --> 0;){
bool matchind = any(Ec == Ea(j));
if(matchind == TRUE){
Ea.shed_row(j);
}
}
return(Ea);
}
//[[Rcpp::export]]
mat update_mstates_arma(const uvec& extantLines, const mat& Q, mat mstates)
{
int u;
vec p_u ;
double sms;
int m = Q.n_rows;
for (int i = 0; i < extantLines.size(); i++){
u = extantLines(i);
p_u = mstates.col(u-1);
mstates.col(u-1) = Q * p_u ;
//~ for (int k = 0; k < m; k++){
//~ mstates(u-1, k) = dot( p_u, Q.col(k));
//~ }
sms = sum(mstates.col(u-1));
mstates.col(u-1) /= sms;
}
return mstates;
}
void calc_overlap(vec &ov,vec &ov_n1,Dres_det dres1,int f1,Dres_det dres2,uvec f2)
{
int n = f2.size();
double cx1 = dres1.x(f1);
double cx2 = dres1.x(f1)+dres1.w(f1)-1;
double cy1 = dres1.y(f1);
double cy2 = dres1.y(f1)+dres1.h(f1)-1;
vec gx1 = dres2.x(f2);
vec gx2 = dres2.x(f2)+dres2.w(f2)-1;
vec gy1 = dres2.y(f2);
vec gy2 = dres2.y(f2)+dres2.h(f2)-1;
double ca = dres1.h(f1)*dres1.w(f1);
vec ga = dres2.h(f2)*dres2.w(f2);
//find the overlapping area
vec xx1 = zeros<vec>(n);
vec yy1 = zeros<vec>(n);
vec xx2 = zeros<vec>(n);
vec yy2 = zeros<vec>(n);
for(int i = 1;i<=n;i++)
{
xx1(i) = max(cx1,gx1(i));
yy1(i) = max(cy1,gy1(i));
xx2(i) = min(cx2,gx2(i));
yy2(i) = min(cy2,gy2(i));
}
vec w = xx2-xx1+1;
vec h = yy2-yy1+1;
uvec inds = find((w>0)*(h>0));
ov = zeros<vec>(n);
ov_n1 = zeros<vec>(n);
if(inds.is_empty() == 0)
{
vec inter = w(inds)*h(inds);
vec u = ca+ga(inds)-w(inds)*h(inds);
ov(inds) = inter/u;
ov_n1(inds) = inter/ca;
}
}
//[[Rcpp::export]]
mat finite_size_correction(const vec& p_a, const vec& A, const uvec& extantLines, mat mstates)
{
// NOTE mstates m X n
int u;
vec rho;
vec rterm;
//~ vec lterm;
double lterm;
vec p_u;
for (int iu = 0; iu < extantLines.size(); iu++){
u = extantLines(iu);
p_u = mstates.col(u-1);
rterm = p_a / ( A - p_u);
rho = A / (A - p_u );
lterm = dot( rho, p_a); //
p_u = p_u % (lterm - rterm) ;
p_u = p_u / sum(p_u ) ;
mstates.col(u - 1) = p_u;
}
return mstates;
}
inline uvec vclip(uvec v, double low = vmin, double high = vmax)/*{{{*/
{
for (int i = 0;i < v.size();i ++)
v[i] = min(max(v[i], vmin), vmax);
return v;
}/*}}}*/
