Home > marl > agent > learnfuns > fullstate_plainq.m

fullstate_plainq

PURPOSE ^

Implements the full-state plain Q-learning algorithm

SYNOPSIS ^

function a = fullstate_plainq(a, state, action, reward, params)

DESCRIPTION ^

Implements the full-state plain Q-learning algorithm
  A = FULLSTATE_PLAINQ(A, STATE, ACTION, REWARD, PARAMS)
  Implements full-state version of the plain Q-learning algorithm,
  employing in addition to that an eligibility trace. Uses flat Q- and
  eligibility tables for fast access.

  Supports discrete states and actions, with 1 action variable per agent.

  Required values on the agent learning parameters:
   alpha           - the learning rate
   gamma           - the discount factor
   lambda          - the eligibility trace decay rate
   epsilon         - the exploration probability
  Required values on the extra parameters:
   newtrial        - only in episodic environments; whether a new trial is
                   beginning

 Can be coupled with an action function that uses a Q-table indexed on
 full world state and agent action, such as fullstate_greedyact().


  See also agent_learn, plainq, fullstate_plainq_init

CROSS-REFERENCE INFORMATION ^

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