deepqlearn.Brain.prototype.policy = function(s) {
  const svol_sx =  this.value_net.layers[0].out_sx;
  const svol_sy =  this.value_net.layers[0].out_sy;
  const svol_depth =  this.value_net.layers[0].out_depth;
  var svol = new convnetjs.Vol(svol_sx, svol_sy, svol_depth);
  svol.w = s;
  var action_values = this.value_net.forward(svol);
  var maxk = 0;
  var maxval = action_values.w[0];
  for(var k=1;k<this.num_actions;k++) {
    if(action_values.w[k] > maxval) { maxk = k; maxval = action_values.w[k]; }
  }
  return {action:maxk, value:maxval};
};```