pg_reinforce.py 文件源码

def __init__(self, session,
                     optimizer,
                     policy_network,
                     state_dim,
                     num_actions,
                     init_exp=0.5,         # initial exploration prob
                     final_exp=0.0,        # final exploration prob
                     anneal_steps=10000,   # N steps for annealing exploration
                     discount_factor=0.99, # discount future rewards
                     reg_param=0.001,      # regularization constants
                     max_gradient=5,       # max gradient norms
                     summary_writer=None,
                     summary_every=100):

    # tensorflow machinery
    self.session        = session
    self.optimizer      = optimizer
    self.summary_writer = summary_writer

    # model components
    self.policy_network = policy_network

    # training parameters
    self.state_dim       = state_dim
    self.num_actions     = num_actions
    self.discount_factor = discount_factor
    self.max_gradient    = max_gradient
    self.reg_param       = reg_param

    # exploration parameters
    self.exploration  = init_exp
    self.init_exp     = init_exp
    self.final_exp    = final_exp
    self.anneal_steps = anneal_steps

    # counters
    self.train_iteration = 0

    # rollout buffer
    self.state_buffer  = []
    self.reward_buffer = []
    self.action_buffer = []

    # record reward history for normalization
    self.all_rewards = []
    self.max_reward_length = 1000000

    # create and initialize variables
    self.create_variables()
    var_lists = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES)
    self.session.run(tf.variables_initializer(var_lists))

    # make sure all variables are initialized
    self.session.run(tf.assert_variables_initialized())

    if self.summary_writer is not None:
      # graph was not available when journalist was created
      self.summary_writer.add_graph(self.session.graph)
      self.summary_every = summary_every