layer: R6 Class Representing a layer in tree for StoSOO

In KosukeHamazaki/myBreedSimulatR: R Breeding Simulator for K.Hamazaki

R6 Class Representing a layer in tree for StoSOO

Description

layer object store specific information on each layer in tree for StoSOO

Public fields

nodesList

[list] List of nodes ('node' class object) in this layer

depth

[numeric] Depth of this layer

optimizeType

[character] Either 'deterministic' for optimizing a deterministic function or 'stochastic' for a stochastic one

nChildrenPerExpansion

[numeric] Number of children per expansion

nNodes

[numeric] Number nodes in this layer

positions

[numeric] Positions of the nodes in this layer

ucbValues

[numeric] Upper confidence bounds of the nodes in this layer

rewardMeans

[numeric] Empirical averages of 'rewards' of the nodes in this layer

isLeaves

[numeric] Are the nodes in this layer leaves of the tree or not

withCheck

[logical] Check arguments for 'node', 'layer', and 'tree' class or not

maxUcbValues

[numeric] Maximum UCB value (or ‘rewardMean' for ’deterministic' function) of the leaf node in the layer

positionMaxUcbValues

[numeric] Position of the leaf node which shows maximum UCB value (or ‘rewardMean' for ’deterministic' function)

maxUcbValuesSoFar

[numeric] Maximum UCB value for the layers shallower than this layer

Methods

Public methods

• layer$new()

• layer$addNodes()

• layer$sortedByPosition()

• layer$evaluateMaximum()

• layer$performOneAction()

• layer$print()

• layer$clone()

---

Method new()

Create a new layer object

Usage

layer$new(
  nodesList,
  depth = NULL,
  optimizeType,
  nChildrenPerExpansion,
  withCheck = FALSE
)

Arguments

nodesList

[list] List of nodes ('node' class object) in this layer

depth

[numeric] Depth of this layer

optimizeType

[character] Either 'deterministic' for optimizing a deterministic function or 'stochastic' for a stochastic one

nChildrenPerExpansion

[numeric] Number of children per expansion

withCheck

[logical] Check arguments for 'node', 'layer', and 'tree' class or not

---

Method addNodes()

Add new nodes to the layer object

Usage

layer$addNodes(newNodesList = NULL)

Arguments

newNodesList

[list] List of new nodes ('node' class object) to be added to this layer

---

Method sortedByPosition()

Sort nodes in this layer by position

Usage

layer$sortedByPosition()

---

Method evaluateMaximum()

Evaluate maximum value of the leaf node in this layer

Usage

layer$evaluateMaximum()

---

Method performOneAction()

Update layer information once

Usage

layer$performOneAction(maxUcbValuesSoFar)

Arguments

maxUcbValuesSoFar

[numeric] Maximum UCB value for the layers shallower than this layer

---

Method print()

Display information about the object

Usage

layer$print()

---

Method clone()

The objects of this class are cloneable with this method.

Usage

layer$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

KosukeHamazaki/myBreedSimulatR documentation built on Aug. 31, 2024, 3:55 p.m.