Home > marl > learn.m

learn

PURPOSE ^

Implements the learning control mechanism

SYNOPSIS ^

function [world, agents, stats] = learn(world, agents, learnparam)

DESCRIPTION ^

Implements the learning control mechanism
  [WORLD, AGENTS, STATS] = LEARN(WORLD, AGENTS, LEARNPARAM)

  Runs the learning algorithms of the agents in the world. Delegates the
  control to either episodic_learn() or continuing_learn(), depending on
  the task type offerred by the world.

  Note that currently, only episodic_learn() is implemented.

  Parameters:
   WORLD       - the world within which the learning takes place.
   AGENTS      - the (possibly heterogeneous) cell array of agents.
               Must be the same with which the world was created.
   LEARNPARAM  - the learning parameters

  Returns:
   WORLD       - the possibly altered world.
   AGENTS      - the (savvier) agents.
   STATS       - the learning statistics.


  See also episodic_learn

CROSS-REFERENCE INFORMATION ^

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