def cnn_lstm(nlstm=128, layer_norm=False, **conv_kwargs):
    def network_fn(X, nenv=1):
        nbatch = X.shape[0] 
        nsteps = nbatch // nenv
         
        h = nature_cnn(X, **conv_kwargs)
       
        M = tf.placeholder(tf.float32, [nbatch]) #mask (done t-1)
        S = tf.placeholder(tf.float32, [nenv, 2*nlstm]) #states

        xs = batch_to_seq(h, nenv, nsteps)
        ms = batch_to_seq(M, nenv, nsteps)

        if layer_norm:
            h5, snew = utils.lnlstm(xs, ms, S, scope='lnlstm', nh=nlstm)
        else:
            h5, snew = utils.lstm(xs, ms, S, scope='lstm', nh=nlstm)
            
        h = seq_to_batch(h5)
        initial_state = np.zeros(S.shape.as_list(), dtype=float)

        return h, {'S':S, 'M':M, 'state':snew, 'initial_state':initial_state}

    return network_fn 

def get_network_builder(name):
    # TODO: replace with reflection? 
    if name == 'cnn':
        return cnn
    elif name == 'cnn_small':
        return cnn_small
    elif name == 'conv_only':
        return conv_only
    elif name == 'mlp':
        return mlp
    elif name == 'lstm':
        return lstm
    elif name == 'cnn_lstm':
        return cnn_lstm
    elif name == 'cnn_lnlstm':
        return cnn_lnlstm
    else:
        raise ValueError('Unknown network type: {}'.format(name)) 

def cnn_lstm(nlstm=128, layer_norm=False, **conv_kwargs):
    def network_fn(X, nenv=1):
        nbatch = X.shape[0]
        nsteps = nbatch // nenv

        h = nature_cnn(X, **conv_kwargs)

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

        xs = batch_to_seq(h, nenv, nsteps)
        ms = batch_to_seq(M, nenv, nsteps)

        if layer_norm:
            h5, snew = utils.lnlstm(xs, ms, S, scope='lnlstm', nh=nlstm)
        else:
            h5, snew = utils.lstm(xs, ms, S, scope='lstm', nh=nlstm)

        h = seq_to_batch(h5)
        initial_state = np.zeros(S.shape.as_list(), dtype=float)

        return h, {'S':S, 'M':M, 'state':snew, 'initial_state':initial_state}

    return network_fn 

def cnn_lstm(nlstm=128, layer_norm=False, conv_fn=nature_cnn, **conv_kwargs):
    def network_fn(X, nenv=1):
        nbatch = X.shape[0]
        nsteps = nbatch // nenv

        h = conv_fn(X, **conv_kwargs)

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

        xs = batch_to_seq(h, nenv, nsteps)
        ms = batch_to_seq(M, nenv, nsteps)

        if layer_norm:
            h5, snew = utils.lnlstm(xs, ms, S, scope='lnlstm', nh=nlstm)
        else:
            h5, snew = utils.lstm(xs, ms, S, scope='lstm', nh=nlstm)

        h = seq_to_batch(h5)
        initial_state = np.zeros(S.shape.as_list(), dtype=float)

        return h, {'S':S, 'M':M, 'state':snew, 'initial_state':initial_state}

    return network_fn 

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)
        nact = ac_space.n
        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)
            pi = fc(h5, 'pi', nact)
            vf = fc(h5, 'v', 1)

        self.pdtype = make_pdtype(ac_space)
        self.pd = self.pdtype.pdfromflat(pi)

        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.pi = pi
        self.vf = vf
        self.step = step
        self.value = value 

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)
        nact = ac_space.n
        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)
            pi = fc(h5, 'pi', nact)
            vf = fc(h5, 'v', 1)

        self.pdtype = make_pdtype(ac_space)
        self.pd = self.pdtype.pdfromflat(pi)

        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.pi = pi
        self.vf = vf
        self.step = step
        self.value = value 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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)

            # lstm
            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)

            pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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)

            # lstm
            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)

            pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

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)
        nact = ac_space.n
        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)
            pi = fc(h5, 'pi', nact)
            vf = fc(h5, 'v', 1)

        self.pdtype = make_pdtype(ac_space)
        self.pd = self.pdtype.pdfromflat(pi)

        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.pi = pi
        self.vf = vf
        self.step = step
        self.value = value 

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)
        nact = ac_space.n
        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)
            pi = fc(h5, 'pi', nact)
            vf = fc(h5, 'v', 1)

        self.pdtype = make_pdtype(ac_space)
        self.pd = self.pdtype.pdfromflat(pi)

        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.pi = pi
        self.vf = vf
        self.step = step
        self.value = value 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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)

            # lstm
            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)

            pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

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)
        nact = ac_space.n
        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)
            pi = fc(h5, 'pi', nact)
            vf = fc(h5, 'v', 1)

        self.pdtype = make_pdtype(ac_space)
        self.pd = self.pdtype.pdfromflat(pi)

        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.pi = pi
        self.vf = vf
        self.step = step
        self.value = value 

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)
        nact = ac_space.n
        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)
            pi = fc(h5, 'pi', nact)
            vf = fc(h5, 'v', 1)

        self.pdtype = make_pdtype(ac_space)
        self.pd = self.pdtype.pdfromflat(pi)

        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.pi = pi
        self.vf = vf
        self.step = step
        self.value = value 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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)

            # lstm
            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)

            pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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)

            # lstm
            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)

            pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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)

            # lstm
            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)

            pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

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)
        nact = ac_space.n
        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)
            pi = fc(h5, 'pi', nact)
            vf = fc(h5, 'v', 1)

        self.pdtype = make_pdtype(ac_space)
        self.pd = self.pdtype.pdfromflat(pi)

        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.pi = pi
        self.vf = vf
        self.step = step
        self.value = value 

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
        self.step = step
        self.value = value 

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
        self.step = step
        self.value = value 

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
        self.step = step
        self.value = value 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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)

            # lstm
            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)

            pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

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
        self.step = step
        self.value = value 

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
        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
        self.step = step
        self.value = value 

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
        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
        self.step = step
        self.value = value 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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)

            # lstm
            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)

            pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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)

            # lstm
            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)

            pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, nlstm=256, reuse=False):
        nbatch = nenv*nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc*nstack)
        nact = ac_space.n
        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 = conv(tf.cast(X, tf.float32)/255., 'c1', nf=32, rf=8, stride=4, init_scale=np.sqrt(2))
            h2 = conv(h, 'c2', nf=64, rf=4, stride=2, init_scale=np.sqrt(2))
            h3 = conv(h2, 'c3', nf=64, rf=3, stride=1, init_scale=np.sqrt(2))
            h3 = conv_to_fc(h3)
            h4 = fc(h3, 'fc1', nh=512, init_scale=np.sqrt(2))
            xs = batch_to_seq(h4, nenv, nsteps)
            ms = batch_to_seq(M, nenv, nsteps)
            h5, snew = lstm(xs, ms, S, 'lstm1', nh=nlstm)
            h5 = seq_to_batch(h5)
            pi = fc(h5, 'pi', nact, act=lambda x:x)
            vf = fc(h5, 'v', 1, act=lambda x:x)

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

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

        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.pi = pi
        self.vf = vf
        self.step = step
        self.value = value 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
        nbatch = nenv * nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc * nstack)
        nact = ac_space.n
        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 = conv(tf.cast(X, tf.float32) / 255., 'c1', nf=32, rf=8, stride=4, init_scale=np.sqrt(2))
            h2 = conv(h, 'c2', nf=64, rf=4, stride=2, init_scale=np.sqrt(2))
            h3 = conv(h2, 'c3', nf=64, rf=3, stride=1, init_scale=np.sqrt(2))
            h3 = conv_to_fc(h3)
            h4 = fc(h3, 'fc1', nh=512, init_scale=np.sqrt(2))

            # lstm
            xs = batch_to_seq(h4, nenv, nsteps)
            ms = batch_to_seq(M, nenv, nsteps)
            h5, snew = lstm(xs, ms, S, 'lstm1', nh=nlstm)
            h5 = seq_to_batch(h5)

            pi_logits = fc(h5, 'pi', nact, act=lambda x: x, init_scale=0.01)
            pi = tf.nn.softmax(pi_logits)
            q = fc(h5, 'q', nact, act=lambda x: x)

        a = sample(pi_logits)  # could change this to use self.pi instead
        self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
        self.X = X
        self.M = M
        self.S = S
        self.pi = pi  # actual policy params now
        self.q = q

        def step(ob, state, mask, *args, **kwargs):
            # returns actions, mus, states
            a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
            return a0, pi0, s

        self.step = step 

def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, nlstm=256, reuse=False):
        nbatch = nenv*nsteps
        nh, nw, nc = ob_space.shape
        ob_shape = (nbatch, nh, nw, nc*nstack)
        nact = ac_space.n
        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 = conv(tf.cast(X, tf.float32)/255., 'c1', nf=32, rf=8, stride=4, init_scale=np.sqrt(2))
            h2 = conv(h, 'c2', nf=64, rf=4, stride=2, init_scale=np.sqrt(2))
            h3 = conv(h2, 'c3', nf=64, rf=3, stride=1, init_scale=np.sqrt(2))
            h3 = conv_to_fc(h3)
            h4 = fc(h3, 'fc1', nh=512, init_scale=np.sqrt(2))
            xs = batch_to_seq(h4, nenv, nsteps)
            ms = batch_to_seq(M, nenv, nsteps)
            h5, snew = lstm(xs, ms, S, 'lstm1', nh=nlstm)
            h5 = seq_to_batch(h5)
            pi = fc(h5, 'pi', nact, act=lambda x:x)
            vf = fc(h5, 'v', 1, act=lambda x:x)

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

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

        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.pi = pi
        self.vf = vf
        self.step = step
        self.value = value 

def lstm(nlstm=128, layer_norm=False):
    """
    Builds LSTM (Long-Short Term Memory) network to be used in a policy.
    Note that the resulting function returns not only the output of the LSTM 
    (i.e. hidden state of lstm for each step in the sequence), but also a dictionary
    with auxiliary tensors to be set as policy attributes. 

    Specifically, 
        S is a placeholder to feed current state (LSTM state has to be managed outside policy)
        M is a placeholder for the mask (used to mask out observations after the end of the episode, but can be used for other purposes too)
        initial_state is a numpy array containing initial lstm state (usually zeros)
        state is the output LSTM state (to be fed into S at the next call)


    An example of usage of lstm-based policy can be found here: common/tests/test_doc_examples.py/test_lstm_example
            
    Parameters:
    ----------

    nlstm: int          LSTM hidden state size

    layer_norm: bool    if True, layer-normalized version of LSTM is used

    Returns:
    -------

    function that builds LSTM with a given input tensor / placeholder
    """
        
    def network_fn(X, nenv=1):
        nbatch = X.shape[0] 
        nsteps = nbatch // nenv
         
        h = tf.layers.flatten(X)

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

        xs = batch_to_seq(h, nenv, nsteps)
        ms = batch_to_seq(M, nenv, nsteps)

        if layer_norm:
            h5, snew = utils.lnlstm(xs, ms, S, scope='lnlstm', nh=nlstm)
        else:
            h5, snew = utils.lstm(xs, ms, S, scope='lstm', nh=nlstm)
            
        h = seq_to_batch(h5)
        initial_state = np.zeros(S.shape.as_list(), dtype=float)

        return h, {'S':S, 'M':M, 'state':snew, 'initial_state':initial_state}

    return network_fn