SYMBOL INDEX (266 symbols across 23 files)

FILE: AccessControl/ServerAccess.py
  class ValueFunction (line 8) | class ValueFunction:
    method __init__ (line 10) | def __init__(self, alpha=0.01, numOfTilings=8, maxSize=2048):
    method getActiveTiles (line 27) | def getActiveTiles(self, n_server, priority, action):
    method value (line 34) | def value(self, state, action):
    method update (line 40) | def update(self, state, action, delta):
    method stateValue (line 48) | def stateValue(self, state):
  class ServerAcess (line 56) | class ServerAcess:
    method __init__ (line 57) | def __init__(self, exp_rate=0.3, lr=0.1, beta=0.01):
    method numFreeServers (line 70) | def numFreeServers(self):
    method chooseAction (line 81) | def chooseAction(self, valueFunc):
    method nxtState (line 95) | def nxtState(self, action):
    method giveReward (line 104) | def giveReward(self, action):
    method run (line 111) | def run(self, valueFunc, steps=1000, inner_steps=100, debug=False):

FILE: AccessControl/TileCoding.py
  class IHT (line 31) | class IHT:
    method __init__ (line 33) | def __init__(self, sizeval):
    method __str__ (line 38) | def __str__(self):
    method count (line 45) | def count (self):
    method fullp (line 48) | def fullp (self):
    method getindex (line 51) | def getindex (self, obj, readonly=False):
  function hashcoords (line 65) | def hashcoords(coordinates, m, readonly=False):
  function tiles (line 73) | def tiles(ihtORsize, numtilings, floats, ints=[], readonly=False):
  function tileswrap (line 88) | def tileswrap (ihtORsize, numtilings, floats, wrapwidths, ints=[], reado...

FILE: BairdExample/BairdCounterExample.py
  class Baird (line 7) | class Baird:
    method __init__ (line 9) | def __init__(self, gamma=0.99, alpha=0.01):
    method chooseAction (line 28) | def chooseAction(self):
    method takeAction (line 35) | def takeAction(self, action):
    method value (line 42) | def value(self, state):
    method run_semi_gradient_TD (line 46) | def run_semi_gradient_TD(self, rounds=100, sarsa=False):
    method run_TDC (line 71) | def run_TDC(self, beta=0.01, rounds=100):

FILE: BlackJack/blackjack_mc.py
  class BlackJackMC (line 6) | class BlackJackMC(object):
    method __init__ (line 8) | def __init__(self):
    method giveCard (line 16) | def giveCard():
    method dealerPolicy (line 21) | def dealerPolicy(self, current_value, usable_ace, is_end):
    method playerPolicy (line 41) | def playerPolicy(self, current_value, usable_ace, is_end):
    method _giveCredit (line 60) | def _giveCredit(self, player_value, dealer_value, is_end=True):
    method play (line 84) | def play(self, rounds=1000):

FILE: BlackJack/blackjack_solution.py
  class BlackJackSolution (line 5) | class BlackJackSolution:
    method __init__ (line 7) | def __init__(self, lr=0.1, exp_rate=0.3):
    method giveCard (line 29) | def giveCard():
    method dealerPolicy (line 34) | def dealerPolicy(self, current_value, usable_ace, is_end):
    method chooseAction (line 53) | def chooseAction(self):
    method playerNxtState (line 75) | def playerNxtState(self, action):
    method winner (line 106) | def winner(self, player_value, dealer_value):
    method _giveCredit (line 128) | def _giveCredit(self, player_value, dealer_value):
    method reset (line 136) | def reset(self):
    method deal2cards (line 141) | def deal2cards(self, show=False):
    method play (line 157) | def play(self, rounds=1000):
    method savePolicy (line 197) | def savePolicy(self, file="policy"):
    method loadPolicy (line 202) | def loadPolicy(self, file="policy"):
    method playWithDealer (line 208) | def playWithDealer(self, rounds=1000):

FILE: CliffWalking/cliffWalking.py
  class Cliff (line 10) | class Cliff:
    method __init__ (line 12) | def __init__(self):
    method nxtPosition (line 19) | def nxtPosition(self, action):
    method giveReward (line 42) | def giveReward(self):
    method show (line 50) | def show(self):
  class Agent (line 68) | class Agent:
    method __init__ (line 69) | def __init__(self, exp_rate=0.3, lr=0.1, sarsa=True):
    method chooseAction (line 84) | def chooseAction(self):
    method reset (line 101) | def reset(self):
    method play (line 106) | def play(self, rounds=10):
  function showRoute (line 145) | def showRoute(states):

FILE: DynaMaze/DynaMaze.py
  class Maze (line 12) | class Maze:
    method __init__ (line 14) | def __init__(self):
    method nxtPosition (line 27) | def nxtPosition(self, action):
    method giveReward (line 43) | def giveReward(self):
    method showMaze (line 50) | def showMaze(self):
  class DynaAgent (line 67) | class DynaAgent:
    method __init__ (line 69) | def __init__(self, exp_rate=0.3, lr=0.1, n_steps=5, episodes=1):
    method chooseAction (line 90) | def chooseAction(self):
    method reset (line 111) | def reset(self):
    method play (line 116) | def play(self):

FILE: DynaMaze/DynaQ+.py
  class Maze (line 11) | class Maze:
    method __init__ (line 13) | def __init__(self):
    method nxtPosition (line 26) | def nxtPosition(self, action):
    method giveReward (line 42) | def giveReward(self):
    method showMaze (line 49) | def showMaze(self):
  class DynaAgentPlus (line 66) | class DynaAgentPlus:
    method __init__ (line 68) | def __init__(self, exp_rate=0.3, lr=0.1, n_steps=5, episodes=1, timeWe...
    method chooseAction (line 91) | def chooseAction(self):
    method reset (line 112) | def reset(self):
    method updateModel (line 118) | def updateModel(self, state, nxtState, action, reward):
    method play (line 129) | def play(self):

FILE: DynaMaze/PrioritySweeping.py
  class Maze (line 12) | class Maze:
    method __init__ (line 14) | def __init__(self):
    method nxtPosition (line 27) | def nxtPosition(self, action):
    method giveReward (line 43) | def giveReward(self):
    method showMaze (line 50) | def showMaze(self):
  class PriorityAgent (line 67) | class PriorityAgent:
    method __init__ (line 69) | def __init__(self, exp_rate=0.3, lr=0.1, n_steps=5, episodes=1, theta=0):
    method chooseAction (line 95) | def chooseAction(self):
    method reset (line 116) | def reset(self):
    method play (line 121) | def play(self):

FILE: GridWorld/gridWorld.py
  class State (line 12) | class State:
    method __init__ (line 13) | def __init__(self, state=START):
    method giveReward (line 20) | def giveReward(self):
    method isEndFunc (line 28) | def isEndFunc(self):
    method nxtPosition (line 32) | def nxtPosition(self, action):
    method showBoard (line 57) | def showBoard(self):
  class Agent (line 76) | class Agent:
    method __init__ (line 78) | def __init__(self):
    method chooseAction (line 91) | def chooseAction(self):
    method takeAction (line 108) | def takeAction(self, action):
    method reset (line 112) | def reset(self):
    method play (line 116) | def play(self, rounds=10):
    method showValues (line 143) | def showValues(self):

FILE: GridWorld/gridWorld_Q.py
  class State (line 11) | class State:
    method __init__ (line 12) | def __init__(self, state=START):
    method giveReward (line 19) | def giveReward(self):
    method isEndFunc (line 27) | def isEndFunc(self):
    method _chooseActionProb (line 31) | def _chooseActionProb(self, action):
    method nxtPosition (line 41) | def nxtPosition(self, action):
    method showBoard (line 73) | def showBoard(self):
  class Agent (line 90) | class Agent:
    method __init__ (line 92) | def __init__(self):
    method chooseAction (line 109) | def chooseAction(self):
    method takeAction (line 127) | def takeAction(self, action):
    method reset (line 132) | def reset(self):
    method play (line 137) | def play(self, rounds=10):

FILE: MountainCar(Lambda)/MountainCar.py
  class ValueFunction (line 11) | class ValueFunction:
    method __init__ (line 13) | def __init__(self, stepSize=0.3, numOfTilings=8, maxSize=2048, lam=0.9...
    method getActiveTiles (line 37) | def getActiveTiles(self, position, velocity, action):
    method value (line 46) | def value(self, position, velocity, action):
    method update (line 53) | def update(self, position, velocity, action, target):
    method costToGo (line 72) | def costToGo(self, position, velocity):
  class MountainCar (line 79) | class MountainCar:
    method __init__ (line 81) | def __init__(self, exp_rate=0.1, debug=True):
    method reset (line 88) | def reset(self):
    method takeAction (line 93) | def takeAction(self, action):
    method chooseAction (line 108) | def chooseAction(self, valueFunc, state):
    method giveReward (line 122) | def giveReward(self, state):
    method play (line 130) | def play(self, valueFunction, rounds=50):

FILE: MountainCar(Lambda)/TileCoding.py
  class IHT (line 31) | class IHT:
    method __init__ (line 33) | def __init__(self, sizeval):
    method __str__ (line 38) | def __str__(self):
    method count (line 45) | def count (self):
    method fullp (line 48) | def fullp (self):
    method getindex (line 51) | def getindex (self, obj, readonly=False):
  function hashcoords (line 65) | def hashcoords(coordinates, m, readonly=False):
  function tiles (line 73) | def tiles(ihtORsize, numtilings, floats, ints=[], readonly=False):
  function tileswrap (line 88) | def tileswrap (ihtORsize, numtilings, floats, wrapwidths, ints=[], reado...

FILE: MountainCar/MountainCar.py
  class ValueFunction (line 11) | class ValueFunction:
    method __init__ (line 13) | def __init__(self, stepSize, numOfTilings=8, maxSize=2048):
    method getActiveTiles (line 30) | def getActiveTiles(self, position, velocity, action):
    method value (line 39) | def value(self, position, velocity, action):
    method update (line 46) | def update(self, position, velocity, action, target):
    method costToGo (line 54) | def costToGo(self, position, velocity):
  class MountainCar (line 61) | class MountainCar:
    method __init__ (line 63) | def __init__(self, n=1, exp_rate=0.1, gamma=1, debug=True):
    method reset (line 72) | def reset(self):
    method takeAction (line 77) | def takeAction(self, action):
    method chooseAction (line 92) | def chooseAction(self, valueFunc):
    method giveReward (line 106) | def giveReward(self):
    method play (line 113) | def play(self, valueFunction, rounds=1):

FILE: MountainCar/TileCoding.py
  class IHT (line 31) | class IHT:
    method __init__ (line 33) | def __init__(self, sizeval):
    method __str__ (line 38) | def __str__(self):
    method count (line 45) | def count (self):
    method fullp (line 48) | def fullp (self):
    method getindex (line 51) | def getindex (self, obj, readonly=False):
  function hashcoords (line 65) | def hashcoords(coordinates, m, readonly=False):
  function tiles (line 73) | def tiles(ihtORsize, numtilings, floats, ints=[], readonly=False):
  function tileswrap (line 88) | def tileswrap (ihtORsize, numtilings, floats, wrapwidths, ints=[], reado...

FILE: Multi-ArmBandit/bandit.py
  class Bandit (line 5) | class Bandit:
    method __init__ (line 6) | def __init__(self, k=10, exp_rate=.3, lr=0.1, ucb=False, seed=None, c=2):
    method chooseAction (line 26) | def chooseAction(self):
    method takeAction (line 43) | def takeAction(self, action):
    method play (line 55) | def play(self, n):

FILE: RandomWalk(General)/RandomWalk.py
  class LinearValueFunction (line 12) | class LinearValueFunction:
    method __init__ (line 14) | def __init__(self, order, method="poly"):
    method value (line 21) | def value(self, state):
    method update (line 26) | def update(self, delta, state):
  class AggValueFunction (line 32) | class AggValueFunction:
    method __init__ (line 34) | def __init__(self, num_groups=10):
    method value (line 39) | def value(self, state):
    method update (line 49) | def update(self, delta, state):
  class RandomWalk (line 55) | class RandomWalk:
    method __init__ (line 57) | def __init__(self, step=1, lr=2e-5, gamma=1, debug=True):
    method chooseAction (line 66) | def chooseAction(self):
    method takeAction (line 70) | def takeAction(self, action):
    method giveReward (line 88) | def giveReward(self):
    method reset (line 95) | def reset(self):
    method play (line 99) | def play(self, valueFunction, rounds=1e5):
  function plot_fig (line 146) | def plot_fig(func):

FILE: RandomWalk(Lambda)/TD_Lambda.py
  class ValueFunction (line 11) | class ValueFunction:
    method __init__ (line 12) | def __init__(self, alpha=0.1):
    method value (line 16) | def value(self, state):
    method learn (line 20) | def learn(self, state, delta):
  class RandomWalk (line 24) | class RandomWalk:
    method __init__ (line 26) | def __init__(self, start=START, end=False, lmbda=0.4, debug=False):
    method chooseAction (line 36) | def chooseAction(self):
    method takeAction (line 40) | def takeAction(self, action):
    method giveReward (line 53) | def giveReward(self, state):
    method reset (line 61) | def reset(self):
    method gt2tn (line 66) | def gt2tn(self, valueFunc, start, end):
    method play (line 73) | def play(self, valueFunc, rounds=100):
  class ValueFunctionTD (line 111) | class ValueFunctionTD:
    method __init__ (line 112) | def __init__(self, alpha=0.1, gamma=0.9, lmbda=0.8):
    method value (line 119) | def value(self, state):
    method updateZ (line 123) | def updateZ(self, state):
    method learn (line 128) | def learn(self, state, nxtState, reward):
  class RWTD (line 134) | class RWTD:
    method __init__ (line 136) | def __init__(self, start=START, end=False, debug=False):
    method chooseAction (line 143) | def chooseAction(self):
    method takeAction (line 147) | def takeAction(self, action):
    method giveReward (line 159) | def giveReward(self, state):
    method reset (line 167) | def reset(self):
    method play (line 172) | def play(self, valueFunc, rounds=100):

FILE: RandomWalk/RandomWalk(n-step).py
  class RandomWalk (line 10) | class RandomWalk:
    method __init__ (line 12) | def __init__(self, n, start=START, end=False, lr=0.1, gamma=1, debug=F...
    method chooseAction (line 34) | def chooseAction(self):
    method takeAction (line 38) | def takeAction(self, action):
    method giveReward (line 51) | def giveReward(self):
    method reset (line 59) | def reset(self):
    method play (line 63) | def play(self, rounds=100):

FILE: ShortCorridor/ShortCorridor.py
  class ShortCorridor (line 4) | class ShortCorridor:
    method __init__ (line 5) | def __init__(self, alpha=0.2, gamma=0.8):
    method softmax (line 13) | def softmax(self, vector):
    method chooseAction (line 16) | def chooseAction(self):
    method takeAction (line 30) | def takeAction(self, action):
    method giveReward (line 41) | def giveReward(self):
    method reset (line 46) | def reset(self):
    method run (line 49) | def run(self, rounds=100):

FILE: TicTacToe/ticTacToe.py
  class State (line 8) | class State:
    method __init__ (line 9) | def __init__(self, p1, p2):
    method getHash (line 19) | def getHash(self):
    method winner (line 23) | def winner(self):
    method availablePositions (line 60) | def availablePositions(self):
    method updateState (line 68) | def updateState(self, position):
    method giveReward (line 74) | def giveReward(self):
    method reset (line 88) | def reset(self):
    method play (line 94) | def play(self, rounds=100):
    method play2 (line 137) | def play2(self):
    method showBoard (line 171) | def showBoard(self):
  class Player (line 188) | class Player:
    method __init__ (line 189) | def __init__(self, name, exp_rate=0.3):
    method getHash (line 197) | def getHash(self, board):
    method chooseAction (line 201) | def chooseAction(self, positions, current_board, symbol):
    method addState (line 221) | def addState(self, state):
    method feedReward (line 225) | def feedReward(self, reward):
    method reset (line 232) | def reset(self):
    method savePolicy (line 235) | def savePolicy(self):
    method loadPolicy (line 240) | def loadPolicy(self, file):
  class HumanPlayer (line 246) | class HumanPlayer:
    method __init__ (line 247) | def __init__(self, name):
    method chooseAction (line 250) | def chooseAction(self, positions):
    method addState (line 259) | def addState(self, state):
    method feedReward (line 263) | def feedReward(self, reward):
    method reset (line 266) | def reset(self):

FILE: TileCoding/tile_coding.py
  function create_tiling (line 4) | def create_tiling(feat_range, bins, offset):
  function create_tilings (line 15) | def create_tilings(feature_ranges, number_tilings, bins, offsets):
  function get_tile_coding (line 39) | def get_tile_coding(feature, tilings):
  class QValueFunction (line 60) | class QValueFunction:
    method __init__ (line 62) | def __init__(self, tilings, actions, lr):
    method value (line 71) | def value(self, state, action):
    method update (line 81) | def update(self, state, action, target):

FILE: WindyGridWorld/windyGridWorld.py
  class State (line 4) | class State:
    method __init__ (line 5) | def __init__(self, state=(3, 0), rows=7, cols=10):
    method giveReward (line 14) | def giveReward(self):
    method nxtPosition (line 20) | def nxtPosition(self, action):
    method showBoard (line 56) | def showBoard(self):
  class Agent (line 76) | class Agent:
    method __init__ (line 78) | def __init__(self, lr=0.2, exp_rate=0.3):
    method chooseAction (line 98) | def chooseAction(self):
    method takeAction (line 116) | def takeAction(self, action):
    method reset (line 121) | def reset(self):
    method play (line 125) | def play(self, rounds=10):