replay
PURPOSE 
Replays the agents' current policies
SYNOPSIS 
function [world, agents, stats] = replay(world, agents, speed, maxiter)
DESCRIPTION 
CROSS-REFERENCE INFORMATION 
This function calls:
- episodic_replay Replays the agents' current policies in an episodic environment
- world Template. Creates a world structure
This function is called by:
- processexp processes a series of experiments ran using runexp()
- learndemo Demonstration of plain Q-learning on a 5x5 gridworld
- replay_algorithm REPLAY_ALGORITHM Runs a given MARL algorithm on a given type of task.
Generated on Wed 04-Aug-2010 16:55:08 by m2html © 2005