Home > marl > rldemo > priv > replay_algorithm.m

replay_algorithm

PURPOSE ^

REPLAY_ALGORITHM Runs a given MARL algorithm on a given type of task.

SYNOPSIS ^

function replay_algorithm(task, cooplev, method, cfg)

DESCRIPTION ^

 REPLAY_ALGORITHM Runs a given MARL algorithm on a given type of task.
  REPLAY_ALGORITHM(TASK, METHOD, CFG)

  Replays a MARL algorithm which was previously run using run_algorithm
  on a given type of task. Specifically designed for use with alg_gui, but
  can also be used independently. Retrieves the algorithm data from the
  field of the 'algdata' structure in the base workspace created by
  run_algorithm. A warning message is displayed if the data for the
  task/algorithm combination is not found.

  Parameters:
   TASK        - specifies the type of task. All task types supported by
       run_algorithm are supported here.
   COOPLEV     - specifies the cooperation level. All levels supported by
       run_algorithm are supported here.
   METHOD      - specifies the algorithm to replay. All algorithms
       supported by run_algorithm are supported here.
   CFG         - configuration of learning process. Structure with the
       following fields (all optional)
       'replayspeed'    - Replay speed, between 0 and 10. Default 6.
   
 See also run_algorithm

CROSS-REFERENCE INFORMATION ^

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