def __init__(self, sess, batch_size, num_episodes, actor_target,
actor_trainer, critic_target, critic_trainer,
trading_state_model, replay_buffer, datacontainer, gamma,
tau):
self.sess = sess
self.batch_size = batch_size
self.num_episodes = num_episodes
self.actor_target = actor_target
self.actor_trainer = actor_trainer
self.critic_target = critic_target
self.critic_trainer = critic_trainer
self.tsm = trading_state_model
self.rpb = replay_buffer
self.datacontainer = datacontainer
self.gamma = gamma
self.tau = tau
self.sess.run(tf.global_variables_initializer())
self.sess.run(
Network.assign_target_graph("actor-trainer", "actor-target"))
self.sess.run(
Network.assign_target_graph("critic-trainer", "critic-target"))
def __init__(self, sess, batch_size, num_episodes, episode_length,
actor_target, actor_trainer, critic_target, critic_trainer,
env, replay_buffer, gamma, tau, actor_noise):
self.sess = sess
self.batch_size = batch_size
self.num_episodes = num_episodes
self.episode_length = episode_length
self.actor_target = actor_target
self.actor_trainer = actor_trainer
self.critic_target = critic_target
self.critic_trainer = critic_trainer
self.env = env
self.rpb = replay_buffer
self.gamma = gamma
self.tau = tau
self.actor_noise = actor_noise
self.sess.run(tf.global_variables_initializer())
self.sess.run(
Network.assign_target_graph("actor-trainer", "actor-target"))
self.sess.run(
Network.assign_target_graph("critic-trainer", "critic-target"))
self.writer = tf.summary.FileWriter("./tensorboard", sess.graph)
self.build_summaries()