rl_example_2.cpp File Reference

#include "cuberl/base/cuberl_types.h"
#include "cuberl/maths/vector_math.h"
#include "cuberl/rl/policies/epsilon_greedy_policy.h"
#include "bitrl/utils/maths/statistics/distributions/beta_dist.h"
#include "bitrl/utils/maths/statistics/distributions/bernoulli_dist.h"
#include "bitrl/envs/multi_armed_bandits/multi_armed_bandits.h"
#include <cmath>
#include <utility>
#include <tuple>
#include <iostream>
#include <random>
#include <algorithm>
#include <numeric>
#include <unordered_map>

Include dependency graph for rl_example_2.cpp:

Classes
struct	rl_example_2::SamplingResult

Namespaces
namespace	rl_example_2

Functions
SamplingResult	rl_example_2::run_epsilon_greedy (MultiArmedBandits &env, real_t eps)
SamplingResult	rl_example_2::run_thompson_sampling (MultiArmedBandits &env)
int	main ()

Variables
uint_t	rl_example_2::N_EPISODES = 1000
real_t	rl_example_2::EPS = 0.2

Function Documentation

main()

int main

(

)

all levers have the same probability of success