bandit.h

Go to the documentation of this file.

/* Brush
copyright 2024 William La Cava
license: GNU/GPL v3
*/
 
#ifndef BANDIT_H
#define BANDIT_H
 
#include "../init.h"
#include "../types.h"
#include "../program/program.h"
#include "../vary/search_space.h"
#include "../util/utils.h"
#include "bandit_operator.h"
#include "dummy.h"
#include "thompson.h"
#include "linear_thompson.h"
 
namespace Brush {
namespace MAB {
 
using namespace Brush;

template <typename T>
struct Bandit
{
    using Iter = tree<Node>::pre_order_iterator;
    
public:
    std::shared_ptr<BanditOperator<T>> pbandit;
    // TODO: This should be a shared pointer to allow multiple instances of Bandit to share the same operator.
     
    std::string type; 
    vector<T> arms; 
 
    std::map<T, float> probabilities; 
 
    Bandit();
    ~Bandit(){};

    Bandit(string type, vector<T> arms);

    Bandit(string type, map<T, float> arms_probs);

    void set_bandit();

    void set_arms(vector<T> arms);

    vector<T> get_arms();

    string get_type();

    void set_type(string type);

    map<T, float> get_probs();

    void set_probs(map<T, float> arms_probs);

    map<T, float> sample_probs(bool update=false);

    T choose(const VectorXf& context);

    void update(T arm, float reward, VectorXf& context);
    
    template <ProgramType PT>
    VectorXf get_context(const Program<PT>& program, Iter spot,
                         const SearchSpace &ss, const Dataset &d);
};
 
//TODO: serialization should save the type of bandit and its parameters
 
} // MAB
} // Brush
#endif