Home > marl > agent > learnfuns > lrn.m

lrn

PURPOSE ^

Implements the learning algorithm of the agent

SYNOPSIS ^

function a = lrn(a, state, actions, rewards, params)

DESCRIPTION ^

Implements the learning algorithm of the agent
  A = LRN(A, STATE, ACTION, REWARD, PARAMS)
  Implements the learning algorithm of the agent. This function is called
  at each learning iteration. The learning behaviour will be initialized
  prior to this function being called.

  This function is a template and performs no operations. This functions'
  input and output argument(s) must conform to the specifications below.
  Any actual implementation of this template must be coupled with an
  implementation of the lrn_init() template.

  Parameters:
   A           - the agent
   STATE       - the agent's view over the world state. A column vector.
   ACTIONS     - the agent's view over the last executed joint action. A
               column vector. 
   REWARDS     - the agent's view over the last received joint reward. A
               column vector. 
   PARAMS      - a structure containing extra information on the basis
               of which the agent may learn.
   Returns:
   A           - the updated agent


  See also agent_control, lrn_init

CROSS-REFERENCE INFORMATION ^

This function calls: This function is called by:
Generated on Wed 04-Aug-2010 16:55:08 by m2html © 2005