std1.0.0-beta-7 SafeC docs

std :: ml::rl

Struct std::BanditAgent

#include <std/ml/rl.h> source

struct BanditAgent {
    int kind;
    unsigned long k;
    &FloatTensor counts;
    &FloatTensor values;
    float param;
    float baseline;
    unsigned long t;
    struct Rng rng;
}

Fields

§int kindsource
§unsigned long ksource

pulls per arm

sample means (preferences for BANDIT_GRADIENT)

§float paramsource
§float baselinesource

mean reward so far

§unsigned long tsource
§struct Rng rngsource

Methods

§unsigned long select()source · definition
§void update(unsigned long arm, float reward)source · definition
§void drop()source · definition
§void free() consumesource · definition

= drop()

§static struct BanditAgent new(int kind, unsigned long k, float param, unsigned long seed)source · definition