Reinforcement Learning Toolbox 2.0
last updated:
General
Documentation
Manual
Tutorial
Class Reference
Master Thesis
Examples
Related Papers
Downloads
Links
News
mailto:webmaster
Main Page     Class Hierarchy   Compound List   File List   Compound Members   File Members

CQGreedyPolicy Class Reference

Greedy Policy based on a Q-Function. More...

#include <cpolicies.h>

Inheritance diagram for CQGreedyPolicy:

CAgentController CActionObject CParameterObject CParameters List of all members.


Public Member Functions

  CQGreedyPolicy (CActionSet *actions, CAbstractQFunction *qFunction)
  ~CQGreedyPolicy ()
virtual CAction getNextAction (CStateCollection *state, CActionDataSet *data=NULL)
  Always returns the greedy action.



Protected Attributes

CAbstractQFunction qFunction
CActionSet availableActions

Detailed Description

Greedy Policy based on a Q-Function.

This policy always takes the greedy action (action with the highest Q-Value). The policy can't be used as stochastic policy, if a stochastic greedy policy is needed take CQStochasticPolicy with a greedy distribution.


Constructor & Destructor Documentation

CQGreedyPolicy::CQGreedyPolicy CActionSet actions,
CAbstractQFunction qFunction
 
CQGreedyPolicy::~CQGreedyPolicy  ) 
 

Member Function Documentation

virtual CAction* CQGreedyPolicy::getNextAction CStateCollection state,
CActionDataSet data = NULL
[virtual]
 

Always returns the greedy action.

Implements CAgentController.


Member Data Documentation

CActionSet* CQGreedyPolicy::availableActions [protected]
 
CAbstractQFunction* CQGreedyPolicy::qFunction [protected]
 

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