Replay.QLearningPersExpPath: Train model of Q learning

Description Usage Arguments

View source: R/QlearningPersExpPath.R

Description

Train model of Q learning

Usage

1
2
3
4
5
6
7
8
9
Replay.QLearningPersExpPath(
  evaluator,
  model.par,
  model.par.surp = NULL,
  model.par.fam = NULL,
  algo.par,
  algo.var,
  game.object
)

Arguments

model.par.surp

If NULL, no suprise model is generated/updated.

model.par.fam

If NULL, no familiarity model is generated/updated.


MartinKies/RLR documentation built on Dec. 24, 2019, 10:02 p.m.