qlearningupdate: qlearningupdate

Description Usage Arguments Details Value Note Author(s) References

Description

This repository implements Q-Learning, a model-free form of reinforcement learning in R.

Usage

1
2
qlearningupdate(q, currentstate, currentaction, currentreward, nextstate=NULL,
  rewardcount=.5, gamma=.25)

Arguments

q

Input state/action matrix.

currentstate

Current state of the game. Does not have to match any of the state for q.

currentaction

Action to take.

currentreward

Reward for currentaction in current iteration.

nextstate

State that the game is in after taking currentaction.

rewardcount

Regularization constant for reward.

gamma

Learning rate constant for Q-Learning.

Details

For internal use for qlearn.

Value

An updated state/action matrix.

Note

Contact at liam.bressler@yale.edu

Author(s)

Liam Bressler

References

http://labressler.github.io/analytics


labressler/QLearning documentation built on May 20, 2019, 7:32 p.m.