24fe3d6576dd8f4cdd5f017805be689d6fa6be8c,baselines/ppo2/policies.py,LstmPolicy,__init__,#LstmPolicy#Any#Any#Any#Any#Any#Any#Any#,57

Before Change

    def __init__(self, sess, ob_space, ac_space, nbatch, nsteps, nlstm=256, reuse=False):
        nenv = nbatch // nsteps

        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc)
        self.pdtype = make_pdtype(ac_space)
        X = tf.placeholder(tf.uint8, ob_shape) //obs
        M = tf.placeholder(tf.float32, [nbatch]) //mask (done t-1)
        S = tf.placeholder(tf.float32, [nenv, nlstm*2]) //states
        with tf.variable_scope("model", reuse=reuse):
            h = nature_cnn(X)
            xs = batch_to_seq(h, nenv, nsteps)
            ms = batch_to_seq(M, nenv, nsteps)
            h5, snew = lstm(xs, ms, S, "lstm1", nh=nlstm)
            h5 = seq_to_batch(h5)
            vf = fc(h5, "v", 1)
            self.pd, self.pi = self.pdtype.pdfromlatent(h5)

        v0 = vf[:, 0]
        a0 = self.pd.sample()
        neglogp0 = self.pd.neglogp(a0)
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)

        def step(ob, state, mask):
            return sess.run([a0, v0, snew, neglogp0], {X:ob, S:state, M:mask})

        def value(ob, state, mask):
            return sess.run(v0, {X:ob, S:state, M:mask})

        self.X = X
        self.M = M
        self.S = S
        self.vf = vf

After Change

    def __init__(self, sess, ob_space, ac_space, nbatch, nsteps, nlstm=256, reuse=False):
        nenv = nbatch // nsteps
        self.pdtype = make_pdtype(ac_space)
        X, processed_x = observation_input(ob_space, nbatch)

        M = tf.placeholder(tf.float32, [nbatch]) //mask (done t-1)
        S = tf.placeholder(tf.float32, [nenv, nlstm*2]) //states

Instances