Class to make decision randomlyDoes nothing more than the interface for DecisionStrategy does. More...

#include <agrum/FMDP/decision/randomDecider.h>

Inheritance diagram for gum::RandomDecider:

Collaboration diagram for gum::RandomDecider:

Public Member Functions
Constructor & destructor.
	RandomDecider ()
	Constructor. More...

	~RandomDecider ()
	Destructor. More...

Incremental methods
void	checkState (const Instantiation &newState, Idx actionId)

ActionSet	stateOptimalPolicy (const Instantiation &curState)

Initialization
virtual void	initialize (const FMDP< double > *fmdp)
	Initializes the learner. More...

Incremental methods
void	setOptimalStrategy (const MultiDimFunctionGraph< ActionSet, SetTerminalNodePolicy > *optPol)

const MultiDimFunctionGraph< ActionSet, SetTerminalNodePolicy > *	_optPol

ActionSet	_allActions

Detailed Description

Class to make decision randomly

Does nothing more than the interface for DecisionStrategy does.

Definition at line 49 of file randomDecider.h.

Constructor & Destructor Documentation

◆ RandomDecider()

gum::RandomDecider::RandomDecider ( )

inline

Constructor.

Definition at line 58 of file randomDecider.h.

58 {}

◆ ~RandomDecider()

gum::RandomDecider::~RandomDecider ( )

inline

Destructor.

Definition at line 63 of file randomDecider.h.

63 {}

Member Function Documentation

◆ checkState()

void gum::RandomDecider::checkState	(	const Instantiation &	newState,
		Idx	actionId
	)

inlinevirtual

Implements gum::IDecisionStrategy.

Definition at line 73 of file randomDecider.h.

73 {}

◆ initialize()

virtual void gum::IDecisionStrategy::initialize ( const FMDP< double > * fmdp )

inlinevirtualinherited

Initializes the learner.

Reimplemented in gum::AdaptiveRMaxPlaner, and gum::E_GreedyDecider.

Definition at line 72 of file IDecisionStrategy.h.

References gum::IDecisionStrategy::_allActions, gum::IDecisionStrategy::_optPol, gum::FMDP< GUM_SCALAR >::beginActions(), gum::IDecisionStrategy::checkState(), gum::FMDP< GUM_SCALAR >::endActions(), and gum::ActionSet::size().

Referenced by gum::E_GreedyDecider::initialize(), gum::AdaptiveRMaxPlaner::initialize(), and gum::SDYNA::initialize().

                                                         {
       _optPol = nullptr;
       if (_allActions.size() == 0)
         for (auto actionIter = fmdp->beginActions();
              actionIter != fmdp->endActions();
              ++actionIter)
           _allActions += *actionIter;
     }

Here is the call graph for this function:

Here is the caller graph for this function:

◆ setOptimalStrategy()

void gum::IDecisionStrategy::setOptimalStrategy ( const MultiDimFunctionGraph< ActionSet, SetTerminalNodePolicy > * optPol )

inlineinherited

Definition at line 90 of file IDecisionStrategy.h.

References gum::IDecisionStrategy::_optPol.

Referenced by gum::SDYNA::makePlanning().

                                                                                 {
       _optPol =
          const_cast< MultiDimFunctionGraph< ActionSet, SetTerminalNodePolicy >* >(
             optPol);
     }

Here is the caller graph for this function:

◆ stateOptimalPolicy()

ActionSet gum::RandomDecider::stateOptimalPolicy ( const Instantiation & curState )

inlinevirtual

Reimplemented from gum::IDecisionStrategy.

Definition at line 75 of file randomDecider.h.

References gum::IDecisionStrategy::_allActions.

                                                                 {
       return _allActions;
     }

Member Data Documentation

◆ _allActions

ActionSet gum::IDecisionStrategy::_allActions

protectedinherited

Definition at line 107 of file IDecisionStrategy.h.

Referenced by gum::IDecisionStrategy::initialize(), stateOptimalPolicy(), gum::E_GreedyDecider::stateOptimalPolicy(), and gum::IDecisionStrategy::stateOptimalPolicy().

◆ _optPol

const MultiDimFunctionGraph< ActionSet, SetTerminalNodePolicy >* gum::IDecisionStrategy::_optPol