Home > marl > episodic_replay.m

episodic_replay

PURPOSE ^

Replays the agents' current policies in an episodic environment

SYNOPSIS ^

function [world, agents, stats] = episodic_replay(world, agents, speed, maxiter)

DESCRIPTION ^

Replays the agents' current policies in an episodic environment
  [WORLD, AGENTS, STATS] = EPISODIC_REPLAY(WORLD, AGENTS, SPEED, MAXITER)
  Parameters:
   WORLD       - the world where the agents live
   AGENTS      - the (possibly heterogeneous) cell array of agents
   SPEED       - the speed of the replay, between 1 and 10
   MAXITER     - for how many iterations to allow the policy to run at
                 most. May be -1 ('run forever').
  Returns:
   WORLD       - the possibly altered world.
   AGENTS      - the possibly altered agents.

  Replays the agents' policies over a single trial. Assumes that the
  agents have already been correctly setup during the learning process.
  Requires that the world implements a view. This view will be shown if
  not already shown.


  See also replay, 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