def __init__()

in baselines/ddpg/ddpg_learner.py [0:0]


    def __init__(self, actor, critic, memory, observation_shape, action_shape, param_noise=None, action_noise=None,
        gamma=0.99, tau=0.001, normalize_returns=False, enable_popart=False, normalize_observations=True,
        batch_size=128, observation_range=(-5., 5.), action_range=(-1., 1.), return_range=(-np.inf, np.inf),
        critic_l2_reg=0., actor_lr=1e-4, critic_lr=1e-3, clip_norm=None, reward_scale=1.):
        # Inputs.
        self.obs0 = tf.placeholder(tf.float32, shape=(None,) + observation_shape, name='obs0')
        self.obs1 = tf.placeholder(tf.float32, shape=(None,) + observation_shape, name='obs1')
        self.terminals1 = tf.placeholder(tf.float32, shape=(None, 1), name='terminals1')
        self.rewards = tf.placeholder(tf.float32, shape=(None, 1), name='rewards')
        self.actions = tf.placeholder(tf.float32, shape=(None,) + action_shape, name='actions')
        self.critic_target = tf.placeholder(tf.float32, shape=(None, 1), name='critic_target')
        self.param_noise_stddev = tf.placeholder(tf.float32, shape=(), name='param_noise_stddev')

        # Parameters.
        self.gamma = gamma
        self.tau = tau
        self.memory = memory
        self.normalize_observations = normalize_observations
        self.normalize_returns = normalize_returns
        self.action_noise = action_noise
        self.param_noise = param_noise
        self.action_range = action_range
        self.return_range = return_range
        self.observation_range = observation_range
        self.critic = critic
        self.actor = actor
        self.actor_lr = actor_lr
        self.critic_lr = critic_lr
        self.clip_norm = clip_norm
        self.enable_popart = enable_popart
        self.reward_scale = reward_scale
        self.batch_size = batch_size
        self.stats_sample = None
        self.critic_l2_reg = critic_l2_reg

        # Observation normalization.
        if self.normalize_observations:
            with tf.variable_scope('obs_rms'):
                self.obs_rms = RunningMeanStd(shape=observation_shape)
        else:
            self.obs_rms = None
        normalized_obs0 = tf.clip_by_value(normalize(self.obs0, self.obs_rms),
            self.observation_range[0], self.observation_range[1])
        normalized_obs1 = tf.clip_by_value(normalize(self.obs1, self.obs_rms),
            self.observation_range[0], self.observation_range[1])

        # Return normalization.
        if self.normalize_returns:
            with tf.variable_scope('ret_rms'):
                self.ret_rms = RunningMeanStd()
        else:
            self.ret_rms = None

        # Create target networks.
        target_actor = copy(actor)
        target_actor.name = 'target_actor'
        self.target_actor = target_actor
        target_critic = copy(critic)
        target_critic.name = 'target_critic'
        self.target_critic = target_critic

        # Create networks and core TF parts that are shared across setup parts.
        self.actor_tf = actor(normalized_obs0)
        self.normalized_critic_tf = critic(normalized_obs0, self.actions)
        self.critic_tf = denormalize(tf.clip_by_value(self.normalized_critic_tf, self.return_range[0], self.return_range[1]), self.ret_rms)
        self.normalized_critic_with_actor_tf = critic(normalized_obs0, self.actor_tf, reuse=True)
        self.critic_with_actor_tf = denormalize(tf.clip_by_value(self.normalized_critic_with_actor_tf, self.return_range[0], self.return_range[1]), self.ret_rms)
        Q_obs1 = denormalize(target_critic(normalized_obs1, target_actor(normalized_obs1)), self.ret_rms)
        self.target_Q = self.rewards + (1. - self.terminals1) * gamma * Q_obs1

        # Set up parts.
        if self.param_noise is not None:
            self.setup_param_noise(normalized_obs0)
        self.setup_actor_optimizer()
        self.setup_critic_optimizer()
        if self.normalize_returns and self.enable_popart:
            self.setup_popart()
        self.setup_stats()
        self.setup_target_network_updates()

        self.initial_state = None # recurrent architectures not supported yet