| 120 | |
| 121 | # approximates V(s) |
| 122 | class ValueModel: |
| 123 | def __init__(self, D, ft, hidden_layer_sizes=[]): |
| 124 | self.ft = ft |
| 125 | self.costs = [] |
| 126 | |
| 127 | # create the graph |
| 128 | self.layers = [] |
| 129 | M1 = D |
| 130 | for M2 in hidden_layer_sizes: |
| 131 | layer = HiddenLayer(M1, M2) |
| 132 | self.layers.append(layer) |
| 133 | M1 = M2 |
| 134 | |
| 135 | # final layer |
| 136 | layer = HiddenLayer(M1, 1, lambda x: x) |
| 137 | self.layers.append(layer) |
| 138 | |
| 139 | # inputs and targets |
| 140 | self.X = tf.placeholder(tf.float32, shape=(None, D), name='X') |
| 141 | self.Y = tf.placeholder(tf.float32, shape=(None,), name='Y') |
| 142 | |
| 143 | # calculate output and cost |
| 144 | Z = self.X |
| 145 | for layer in self.layers: |
| 146 | Z = layer.forward(Z) |
| 147 | Y_hat = tf.reshape(Z, [-1]) # the output |
| 148 | self.predict_op = Y_hat |
| 149 | |
| 150 | cost = tf.reduce_sum(tf.square(self.Y - Y_hat)) |
| 151 | self.cost = cost |
| 152 | self.train_op = tf.train.AdamOptimizer(1e-1).minimize(cost) |
| 153 | |
| 154 | def set_session(self, session): |
| 155 | self.session = session |
| 156 | |
| 157 | def partial_fit(self, X, Y): |
| 158 | X = np.atleast_2d(X) |
| 159 | X = self.ft.transform(X) |
| 160 | Y = np.atleast_1d(Y) |
| 161 | self.session.run(self.train_op, feed_dict={self.X: X, self.Y: Y}) |
| 162 | cost = self.session.run(self.cost, feed_dict={self.X: X, self.Y: Y}) |
| 163 | self.costs.append(cost) |
| 164 | |
| 165 | def predict(self, X): |
| 166 | X = np.atleast_2d(X) |
| 167 | X = self.ft.transform(X) |
| 168 | return self.session.run(self.predict_op, feed_dict={self.X: X}) |
| 169 | |
| 170 | |
| 171 | def play_one_td(env, pmodel, vmodel, gamma): |