AgentMDP Class Reference

AgentMDP represents an agent which uses a MDP-based policy. More...

#include <AgentMDP.h>

Inheritance diagram for AgentMDP:

Public Member Functions
Index	Act (Index sI, Index joI, double reward)
	Return an individual action based on state, last joint observation and reward. More...
	AgentMDP (const PlanningUnitDecPOMDPDiscrete *pu, Index id, const QTable &Q)
	(default) Constructor More...
	AgentMDP (const AgentMDP &a)
	Copy constructor. More...
void	ResetEpisode ()
	Will be called before an episode, to reinitialize the agent. More...
	~AgentMDP ()
	Destructor. More...
Public Member Functions inherited from AgentFullyObservable
	AgentFullyObservable (const PlanningUnitDecPOMDPDiscrete *pu, Index id)
	(default) Constructor More...
	AgentFullyObservable (const AgentFullyObservable &a)
	Copy constructor. More...
	~AgentFullyObservable ()
	Destructor. More...
Public Member Functions inherited from AgentDecPOMDPDiscrete
	AgentDecPOMDPDiscrete (const PlanningUnitDecPOMDPDiscrete *pu, Index id)
	(default) Constructor More...
	AgentDecPOMDPDiscrete (const AgentDecPOMDPDiscrete &a)
	Copy constructor. More...
const PlanningUnitDecPOMDPDiscrete *	GetPU () const
Public Member Functions inherited from SimulationAgent
virtual Index	GetIndex () const
	Retrieves the index of this agent. More...
virtual bool	GetVerbose () const
	If true, the agent will report more. More...
void	Print () const
	Print out some information about this agent. More...
virtual void	SetIndex (Index id)
	Sets the index of this agent. More...
virtual void	SetVerbose (bool verbose)
	Set whether this agent should be verbose. More...
	SimulationAgent (Index id, bool verbose=false)
	(default) Constructor More...
virtual std::string	SoftPrint () const
	Return some information about this agent. More...
virtual	~SimulationAgent ()
	Destructor. More...

Private Attributes
QTable	_m_Q
size_t	_m_t

Detailed Description

AgentMDP represents an agent which uses a MDP-based policy.

In particular, AgentMDP takes actions based upon states by looking up the maximizing action in the QTable (_m_Q) that this agent receives upon construction. This is in contrast to other AgentFullyObservable types that do some actual learning or planning during the simulation.

Constructor & Destructor Documentation

AgentMDP::AgentMDP	(	const PlanningUnitDecPOMDPDiscrete *	pu,
		Index	id,
		const QTable &	Q
	)

(default) Constructor

AgentMDP::AgentMDP

(

const AgentMDP &

a

)

Copy constructor.

AgentMDP::~AgentMDP

(

)

Destructor.

Member Function Documentation

Index AgentMDP::Act ( Index  sI, Index  joI, double  reward  )

virtual

Return an individual action based on state, last joint observation and reward.

Implements AgentFullyObservable.

References _m_Q, _m_t, SimulationAgent::GetIndex(), PlanningUnitMADPDiscrete::GetNrJointActions(), AgentDecPOMDPDiscrete::GetPU(), and PlanningUnitMADPDiscrete::JointToIndividualActionIndices().

void AgentMDP::ResetEpisode ( )

virtual

Will be called before an episode, to reinitialize the agent.

Implements SimulationAgent.

References _m_t.

Member Data Documentation

QTable AgentMDP::_m_Q

private

Referenced by Act().

size_t AgentMDP::_m_t

private

Referenced by Act(), and ResetEpisode().