Home > marl > agent > actfuns > greedyact.m

greedyact

PURPOSE ^

Implements deterministic greedy action selection for Q-learners

SYNOPSIS ^

function [a, action] = greedyact(a, state, actions, rewards, params)

DESCRIPTION ^

Implements deterministic greedy action selection for Q-learners
  [A, ACTION] = GREEDYACT(A, STATE, ACTIONS, REWARDS, PARAMS)
  Implements greedy deterministic action selection, using a Q-table
  indexed by the agent's state and action. The action with the highest
  Q-value is chosen (breaking ties randomly).

  Supports discrete states and actions, with 1 action variable only.

  Requires the size of the Q-table to be cached under a field named
  'qsize'.

  See also act

CROSS-REFERENCE INFORMATION ^

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