MultiAgentDecisionProcess
PartialJointPolicy Class Reference

PartialJointPolicy represents a joint policy that is only specified for t time steps instead of for every time step. More...

#include <PartialJointPolicy.h>

Inheritance diagram for PartialJointPolicy:
[legend]

Public Member Functions

double GetPastReward () const
 
PartialJointPolicyoperator= (const PartialJointPolicy &o)
 Destructor. More...
 
 PartialJointPolicy (double r=0.0)
 (default) Constructor More...
 
 PartialJointPolicy (const PartialJointPolicy &a)
 Copy constructor. More...
 
void SetPastReward (double r)
 

Private Attributes

double _m_pastReward
 Stores the past reward the partial policy achieves. More...
 

Detailed Description

PartialJointPolicy represents a joint policy that is only specified for t time steps instead of for every time step.

I.e., it is specified for time steps 0 until t, instead of 0 until horizon.

Constructor & Destructor Documentation

PartialJointPolicy::PartialJointPolicy ( double  r = 0.0)
inline

(default) Constructor

PartialJointPolicy::PartialJointPolicy ( const PartialJointPolicy a)
inline

Copy constructor.

Member Function Documentation

PartialJointPolicy & PartialJointPolicy::operator= ( const PartialJointPolicy o)

Destructor.

Copy assignment operator

References _m_pastReward.

Referenced by PartialJointPolicyDiscretePure::operator=().

void PartialJointPolicy::SetPastReward ( double  r)
inline

Member Data Documentation

double PartialJointPolicy::_m_pastReward
private

Stores the past reward the partial policy achieves.

Referenced by GetPastReward(), and operator=().