qlearn

Description

Input a game that has variables statevars (which the player can keep track of). The player can perform any of possibleactions. The output matrix will give the expected value of each action (column) in each state (row).

Usage

qlearn(game, statevars, possibleactions, playername="P1",
  numiter=1000, prevstrategy=NULL, ...)

Arguments

Details

At some point in game, there must be a line of the format

playername <- 'Choose'

where playername is substituted with the paramater "playername". This line should be at the point where the user wants to have the player choose an action. Since playername defaults to "P1", it sufficient to put the line:

P1 <- 'Choose'

somewhere in the function.

Value

A matrix describing the expected reward values of performing a certain action (columns) in a certain state (rows).

Note

Contact at liam.bressler@yale.edu

Author(s)

Liam Bressler

References

http://labressler.github.io/analytics

Examples

cardgame <- function()
{
  playercards <- sample(1:8,4) #distribute the cards, we're player one
  ourcard <- playercards[1] #our card
  playertotals <- rep(-1,4) #including the antes
  playersinpot <- vector()
  for (player in 2:4) #other 3 players go first
  {
    if (playercards[player]>=2)
    {
      playertotals[player] <- (-3)
      playersinpot <- append(playersinpot,player)
    }
  }
  #the next line is where we want to choose our action
  player1 <- 'Choose'
  if (player1=="Call")
  {
    playertotals[1] <- (-3)
    playersinpot <- append(playersinpot,1)
  }
  potsize <- -1*(sum(playertotals)) #the amount in the pot is how much the players put in
  playercards[!(1:4 %in% playersinpot)] <- 0 #get rid of everyone who folded
  winner <- which.max(playercards) #winner is the person with the highest card who didn't fold
  playertotals[winner] <- playertotals[winner]+potsize
  return(playertotals[1]) #return how much we won
}

strat <- qlearn(game="cardgame",statevars="ourcard",possibleactions=c("Call","Fold"),
  playername="player1",numiter=25000) #make sure each function and variable name is a string

strat

qlearningaction

Description

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

Usage

qlearningaction(q, currentstate, exploration=.5)

Arguments

Details

For internal use for qlearn.

Value

An action to take, taken from the possible actions of q.

Note

Contact at liam.bressler@yale.edu

Author(s)

Liam Bressler

References

http://labressler.github.io/analytics

Examples

cardgame <- function()
{
  playercards <- sample(1:8,4) #distribute the cards, we're player one
  ourcard <- playercards[1] #our card
  playertotals <- rep(-1,4) #including the antes
  playersinpot <- vector()
  for (player in 2:4) #other 3 players go first
  {
    if (playercards[player]>=2)
    {
      playertotals[player] <- (-3)
      playersinpot <- append(playersinpot,player)
    }
  }
  #the next line is where we want to choose our action
  player1 <- 'Choose'
  if (player1=="Call")
  {
    playertotals[1] <- (-3)
    playersinpot <- append(playersinpot,1)
  }
  potsize <- -1*(sum(playertotals)) #the amount in the pot is how much the players put in
  playercards[!(1:4 %in% playersinpot)] <- 0 #get rid of everyone who folded
  winner <- which.max(playercards) #winner is the person with the highest card who didn't fold
  playertotals[winner] <- playertotals[winner]+potsize
  return(playertotals[1]) #return how much we won
}

strat <- qlearn(game="cardgame",statevars="ourcard",possibleactions=c("Call","Fold"),
  playername="player1",numiter=25000) #make sure each function and variable name is a string

qlearningaction(strat,3,exploration=.75)
#Pick an action to perform when we have the 3 card, with high exploration

qlearningupdate

Description

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

Usage

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

Arguments

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

Examples

cardgame <- function()
{
  playercards <- sample(1:8,4) #distribute the cards, we're player one
  ourcard <- playercards[1] #our card
  playertotals <- rep(-1,4) #including the antes
  playersinpot <- vector()
  for (player in 2:4) #other 3 players go first
  {
    if (playercards[player]>=2)
    {
      playertotals[player] <- (-3)
      playersinpot <- append(playersinpot,player)
    }
  }
  #the next line is where we want to choose our action
  player1 <- 'Choose'
  if (player1=="Call")
  {
    playertotals[1] <- (-3)
    playersinpot <- append(playersinpot,1)
  }
  potsize <- -1*(sum(playertotals)) #the amount in the pot is how much the players put in
  playercards[!(1:4 %in% playersinpot)] <- 0 #get rid of everyone who folded
  winner <- which.max(playercards) #winner is the person with the highest card who didn't fold
  playertotals[winner] <- playertotals[winner]+potsize
  return(playertotals[1]) #return how much we won
}

strat <- qlearn(game="cardgame",statevars="ourcard",possibleactions=c("Call","Fold"),
  playername="player1",numiter=25000) #make sure each function and variable name is a string

strat <- qlearningupdate(strat,currentstate=7,currentaction="Call",currentreward=5)
#Update the matrix after an example when we call with the 7 card as our state, winning 5 chips