gum::IDecisionStrategy Class Reference

<agrum/FMDP/SDyna/IDecisionStrategy.h> More...

#include <IDecisionStrategy.h>

Inheritance diagram for gum::IDecisionStrategy:

Collaboration diagram for gum::IDecisionStrategy:

Public Member Functions
Constructor & destructor.
virtual	~IDecisionStrategy ()=default
	Destructor (virtual and empty since it's an interface).
Initialization
virtual void	initialize (const FMDP< double > *fmdp)
	Initializes the learner.

Incremental methods
const MultiDimFunctionGraph< ActionSet, SetTerminalNodePolicy > *	optPol_ {nullptr}
ActionSet	allActions_
virtual void	checkState (const Instantiation &newState, Idx actionId)=0
void	setOptimalStrategy (MultiDimFunctionGraph< ActionSet, SetTerminalNodePolicy > *optPol)
virtual ActionSet	stateOptimalPolicy (const Instantiation &curState)

Detailed Description

<agrum/FMDP/SDyna/IDecisionStrategy.h>

Interface for manipulating decision center

Definition at line 70 of file IDecisionStrategy.h.

Constructor & Destructor Documentation

~IDecisionStrategy()

virtual gum::IDecisionStrategy::~IDecisionStrategy ( )

virtualdefault

Destructor (virtual and empty since it's an interface).

Member Function Documentation

checkState()

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

pure virtual

Implemented in gum::AdaptiveRMaxPlaner, gum::E_GreedyDecider, gum::LazyDecider, gum::RandomDecider, and gum::StatisticalLazyDecider.

initialize()

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

virtual

Initializes the learner.

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

Definition at line 48 of file IDecisionStrategy_inl.h.

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

References allActions_, gum::FMDP< GUM_ELEMENT >::beginActions(), gum::FMDP< GUM_ELEMENT >::endActions(), and optPol_.

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

Here is the call graph for this function:

Here is the caller graph for this function:

setOptimalStrategy()

INLINE void gum::IDecisionStrategy::setOptimalStrategy

(

MultiDimFunctionGraph< ActionSet, SetTerminalNodePolicy > *

optPol

)

Definition at line 55 of file IDecisionStrategy_inl.h.

                                                                         {
    optPol_ = optPol;
  }

References optPol_.

stateOptimalPolicy()

INLINE ActionSet gum::IDecisionStrategy::stateOptimalPolicy ( const Instantiation & curState )

virtual

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

Definition at line 60 of file IDecisionStrategy_inl.h.

                                                                                      {
    return (optPol_ && optPol_->realSize() != 0) ? optPol_->get(curState) : allActions_;
  }

References allActions_, and optPol_.

Referenced by gum::E_GreedyDecider::stateOptimalPolicy().

Here is the caller graph for this function:

Member Data Documentation

allActions_

ActionSet gum::IDecisionStrategy::allActions_

protected

Definition at line 115 of file IDecisionStrategy.h.

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

optPol_

const MultiDimFunctionGraph< ActionSet, SetTerminalNodePolicy >* gum::IDecisionStrategy::optPol_ {nullptr}

protected

Definition at line 112 of file IDecisionStrategy.h.

{nullptr};

Referenced by initialize(), setOptimalStrategy(), and stateOptimalPolicy().

---

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

• agrum/FMDP/SDyna/Strategies/IDecisionStrategy.h
• agrum/FMDP/SDyna/Strategies/IDecisionStrategy_inl.h