ValueTable: Value Table

In markdumke/reinforceR: Reinforcement Learning

Value Table

Description

Table representing the action value function Q.

Arguments

n.states	[integer(1)] Number of states (rows in the value function).
n.actions	[integer(1)] Number of actions (columns in the value function).
step.size	[numeric(1)] Step size (learning rate) for gradient descent update.

Details

You can specify the shape of the value table. If omitted the agent will try to configure these automatically from the environment during interaction (therefore the environment needs to have a n.states and n.actions attribute).

Usage

makeValueFunction("table", n.states = NULL, n.actions = 1L, step.size = 0.1, initial.value = NULL)

Examples

val = makeValueFunction("table", n.states = 20L, n.actions = 4L)

markdumke/reinforceR documentation built on Nov. 17, 2022, 12:53 a.m.