MultiAgentDecisionProcess
|
PartialJointPolicy represents a joint policy that is only specified for t time steps instead of for every time step. More...
#include <PartialJointPolicy.h>
Public Member Functions | |
double | GetPastReward () const |
PartialJointPolicy & | operator= (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... | |
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.
|
inline |
(default) Constructor
|
inline |
Copy constructor.
|
inline |
PartialJointPolicy & PartialJointPolicy::operator= | ( | const PartialJointPolicy & | o | ) |
Destructor.
Copy assignment operator
References _m_pastReward.
Referenced by PartialJointPolicyDiscretePure::operator=().
|
inline |
|
private |
Stores the past reward the partial policy achieves.
Referenced by GetPastReward(), and operator=().