SYMBOL INDEX (157 symbols across 14 files)

FILE: model-in-product/sklearn-jpmml/pmml_demo/src/main/java/PMMLDemo.java
  class PMMLDemo (line 28) | public class PMMLDemo {
    method loadPmml (line 29) | private Evaluator loadPmml(){
    method predict (line 60) | private int predict(Evaluator evaluator,int a, int b, int c, int d) {
    method main (line 92) | public static void main(String args[]){

FILE: model-in-product/tensorflow-java/TFDemoJava/src/main/java/TFjavaDemo.java
  class TFjavaDemo (line 22) | public class TFjavaDemo {
    method main (line 23) | public static void main(String args[]){
    method loadTensorflowModel (line 51) | static private byte[] loadTensorflowModel(String path){
    method covertArrayToTensor (line 60) | static private Tensor<Float> covertArrayToTensor(float inputs[][]){

FILE: reinforcement-learning/a3c.py
  class ACNet (line 44) | class ACNet(object):
    method __init__ (line 45) | def __init__(self, scope, globalAC=None):
    method _build_net (line 83) | def _build_net(self, scope):
    method update_global (line 95) | def update_global(self, feed_dict):  # run by a local
    method pull_global (line 98) | def pull_global(self):  # run by a local
    method choose_action (line 101) | def choose_action(self, s):  # run by a local
  class Worker (line 108) | class Worker(object):
    method __init__ (line 109) | def __init__(self, name, globalAC):
    method work (line 114) | def work(self):

FILE: reinforcement-learning/actor_critic.py
  class Actor (line 21) | class Actor():
    method __init__ (line 22) | def __init__(self, env, sess):
    method create_softmax_network (line 33) | def create_softmax_network(self):
    method weight_variable (line 57) | def weight_variable(self, shape):
    method bias_variable (line 61) | def bias_variable(self, shape):
    method choose_action (line 65) | def choose_action(self, observation):
    method learn (line 71) | def learn(self, state, action, td_error):
  class Critic (line 88) | class Critic():
    method __init__ (line 89) | def __init__(self, env, sess):
    method create_Q_network (line 103) | def create_Q_network(self):
    method create_training_method (line 115) | def create_training_method(self):
    method train_Q_network (line 125) | def train_Q_network(self, state, reward, next_state):
    method weight_variable (line 132) | def weight_variable(self,shape):
    method bias_variable (line 136) | def bias_variable(self,shape):
  function main (line 146) | def main():

FILE: reinforcement-learning/ddpg.py
  class DDPG (line 44) | class DDPG(object):
    method __init__ (line 45) | def __init__(self, a_dim, s_dim, a_bound,):
    method choose_action (line 84) | def choose_action(self, s):
    method learn (line 87) | def learn(self):
    method store_transition (line 101) | def store_transition(self, s, a, r, s_):
    method _build_a (line 107) | def _build_a(self, s, scope, trainable):
    method _build_c (line 113) | def _build_c(self, s, a, scope, trainable):

FILE: reinforcement-learning/ddqn.py
  class DQN (line 25) | class DQN():
    method __init__ (line 27) | def __init__(self, env):
    method create_Q_network (line 43) | def create_Q_network(self):
    method create_training_method (line 75) | def create_training_method(self):
    method perceive (line 82) | def perceive(self,state,action,reward,next_state,done):
    method train_Q_network (line 92) | def train_Q_network(self):
    method egreedy_action (line 121) | def egreedy_action(self,state):
    method action (line 132) | def action(self,state):
    method update_target_q_network (line 137) | def update_target_q_network(self, episode):
    method weight_variable (line 143) | def weight_variable(self,shape):
    method bias_variable (line 147) | def bias_variable(self,shape):
  function main (line 157) | def main():

FILE: reinforcement-learning/ddqn_prioritised_replay.py
  class SumTree (line 27) | class SumTree(object):
    method __init__ (line 35) | def __init__(self, capacity):
    method add (line 44) | def add(self, p, data):
    method update (line 53) | def update(self, tree_idx, p):
    method get_leaf (line 61) | def get_leaf(self, v):
    method total_p (line 91) | def total_p(self):
  class Memory (line 95) | class Memory(object):  # stored as ( s, a, r, s_ ) in SumTree
    method __init__ (line 106) | def __init__(self, capacity):
    method store (line 109) | def store(self, transition):
    method sample (line 115) | def sample(self, n):
    method batch_update (line 132) | def batch_update(self, tree_idx, abs_errors):
  class DQN (line 139) | class DQN():
    method __init__ (line 141) | def __init__(self, env):
    method create_Q_network (line 158) | def create_Q_network(self):
    method create_training_method (line 191) | def create_training_method(self):
    method store_transition (line 199) | def store_transition(self, s, a, r, s_, done):
    method perceive (line 203) | def perceive(self,state,action,reward,next_state,done):
    method train_Q_network (line 212) | def train_Q_network(self):
    method egreedy_action (line 248) | def egreedy_action(self,state):
    method action (line 259) | def action(self,state):
    method update_target_q_network (line 264) | def update_target_q_network(self, episode):
    method weight_variable (line 270) | def weight_variable(self,shape):
    method bias_variable (line 274) | def bias_variable(self,shape):
  function main (line 284) | def main():

FILE: reinforcement-learning/dqn.py
  class DQN (line 24) | class DQN():
    method __init__ (line 26) | def __init__(self, env):
    method create_Q_network (line 42) | def create_Q_network(self):
    method create_training_method (line 55) | def create_training_method(self):
    method perceive (line 62) | def perceive(self,state,action,reward,next_state,done):
    method train_Q_network (line 72) | def train_Q_network(self):
    method egreedy_action (line 97) | def egreedy_action(self,state):
    method action (line 108) | def action(self,state):
    method weight_variable (line 113) | def weight_variable(self,shape):
    method bias_variable (line 117) | def bias_variable(self,shape):
  function main (line 127) | def main():

FILE: reinforcement-learning/duel_dqn.py
  class DQN (line 25) | class DQN():
    method __init__ (line 27) | def __init__(self, env):
    method create_Q_network (line 43) | def create_Q_network(self):
    method create_training_method (line 97) | def create_training_method(self):
    method perceive (line 104) | def perceive(self,state,action,reward,next_state,done):
    method train_Q_network (line 114) | def train_Q_network(self):
    method egreedy_action (line 139) | def egreedy_action(self,state):
    method action (line 150) | def action(self,state):
    method update_target_q_network (line 155) | def update_target_q_network(self, episode):
    method weight_variable (line 161) | def weight_variable(self,shape):
    method bias_variable (line 165) | def bias_variable(self,shape):
  function main (line 175) | def main():

FILE: reinforcement-learning/introduction.py
  class State (line 20) | class State:
    method __init__ (line 21) | def __init__(self):
    method hash (line 32) | def hash(self):
    method is_end (line 42) | def is_end(self):
    method next_state (line 84) | def next_state(self, i, j, symbol):
    method print (line 91) | def print(self):
  function get_all_states_impl (line 106) | def get_all_states_impl(current_state, current_symbol, all_states):
  function get_all_states (line 118) | def get_all_states():
  class Judger (line 129) | class Judger:
    method __init__ (line 133) | def __init__(self, player1, player2):
    method reset (line 143) | def reset(self):
    method alternate (line 147) | def alternate(self):
    method play (line 153) | def play(self, print=False):
  class Player (line 174) | class Player:
    method __init__ (line 177) | def __init__(self, step_size=0.1, epsilon=0.1):
    method reset (line 184) | def reset(self):
    method set_state (line 188) | def set_state(self, state):
    method set_symbol (line 192) | def set_symbol(self, symbol):
    method backup (line 208) | def backup(self):
    method act (line 222) | def act(self):
    method save_policy (line 247) | def save_policy(self):
    method load_policy (line 251) | def load_policy(self):
  class HumanPlayer (line 260) | class HumanPlayer:
    method __init__ (line 261) | def __init__(self, **kwargs):
    method reset (line 267) | def reset(self):
    method set_state (line 270) | def set_state(self, state):
    method set_symbol (line 273) | def set_symbol(self, symbol):
    method backup (line 277) | def backup(self, _):
    method act (line 280) | def act(self):
  function train (line 288) | def train(epochs):
  function compete (line 307) | def compete(turns):
  function play (line 326) | def play():

FILE: reinforcement-learning/nature_dqn.py
  class DQN (line 25) | class DQN():
    method __init__ (line 27) | def __init__(self, env):
    method create_Q_network (line 43) | def create_Q_network(self):
    method create_training_method (line 75) | def create_training_method(self):
    method perceive (line 82) | def perceive(self,state,action,reward,next_state,done):
    method train_Q_network (line 92) | def train_Q_network(self):
    method egreedy_action (line 117) | def egreedy_action(self,state):
    method action (line 128) | def action(self,state):
    method update_target_q_network (line 133) | def update_target_q_network(self, episode):
    method weight_variable (line 139) | def weight_variable(self,shape):
    method bias_variable (line 143) | def bias_variable(self,shape):
  function main (line 153) | def main():

FILE: reinforcement-learning/policy_gradient.py
  class Policy_Gradient (line 21) | class Policy_Gradient():
    method __init__ (line 22) | def __init__(self, env):
    method create_softmax_network (line 34) | def create_softmax_network(self):
    method weight_variable (line 56) | def weight_variable(self, shape):
    method bias_variable (line 60) | def bias_variable(self, shape):
    method choose_action (line 64) | def choose_action(self, observation):
    method store_transition (line 69) | def store_transition(self, s, a, r):
    method learn (line 74) | def learn(self):
  function main (line 99) | def main():

FILE: reinforcement-learning/q_learning_windy_world.py
  function step (line 44) | def step(state, action):
  function episode (line 58) | def episode(q_value):
  function q_learning (line 91) | def q_learning():

FILE: reinforcement-learning/sarsa_windy_world.py
  function step (line 44) | def step(state, action):
  function episode (line 58) | def episode(q_value):
  function sarsa (line 90) | def sarsa():