cpid::EpsGreedySampler Class Reference

This sampler expects as input an unordered_map<string, Variant> containing an entry QKey, which is a tensor of size [b, n]. More...

#include <sampler.h>

Inherits cpid::BaseSampler.

Public Member Functions
	EpsGreedySampler (double eps=0.07, const std::string &QKey=kQKey, const std::string &actionKey=kActionKey)
ag::Variant	sample (ag::Variant in) override
Public Member Functions inherited from cpid::BaseSampler
	BaseSampler ()
virtual	~BaseSampler ()=default
virtual ag::Variant	computeProba (const ag::Variant &in, const ag::Variant &action)

Public Attributes
double	eps_
std::string	QKey_
std::string	actionKey_

Detailed Description

This sampler expects as input an unordered_map<string, Variant> containing an entry QKey, which is a tensor of size [b, n].

It outputs the same map, with a new key actionKey, which contains the best action with proba 1-eps, and a random action with proba eps.

Constructor & Destructor Documentation

cpid::EpsGreedySampler::EpsGreedySampler	(	double	eps = 0.07,
		const std::string &	QKey = kQKey,
		const std::string &	actionKey = kActionKey
	)

Member Function Documentation

ag::Variant cpid::EpsGreedySampler::sample ( ag::Variant  in )

overridevirtual

Reimplemented from cpid::BaseSampler.

Member Data Documentation

std::string cpid::EpsGreedySampler::actionKey_

double cpid::EpsGreedySampler::eps_

std::string cpid::EpsGreedySampler::QKey_

---

The documentation for this class was generated from the following files:

• cpid/sampler.h
• cpid/sampler.cpp