[Fixed BC with LSTM] (#766)

Fixes the issue raised by @hsaikia in #552
Added the memory_size variable to the BC model
Added memory_size and recurrent_out to the output nodes of the graph when using BC with LSTM

python/unitytrainers/bc/models.py

         self.dropout_rate = tf.placeholder(dtype=tf.float32, shape=[], name="dropout_rate")
         hidden_reg = tf.layers.dropout(hidden, self.dropout_rate)
         if self.use_recurrent:
+            tf.Variable(self.m_size, name="memory_size", trainable=False, dtype=tf.int32)
             self.memory_in = tf.placeholder(shape=[None, self.m_size], dtype=tf.float32, name='recurrent_in')
             hidden_reg, self.memory_out = self.create_recurrent_encoder(hidden_reg, self.memory_in)
             self.memory_out = tf.identity(self.memory_out, name='recurrent_out')

python/unitytrainers/trainer_controller.py

                 scopes += [scope]
                 if self.trainers[brain_name].parameters["trainer"] == "imitation":
                     nodes += [scope + x for x in ["action"]]
-                elif not self.trainers[brain_name].parameters["use_recurrent"]:
+                else:
-                else:
-                    node_list = ["action", "value_estimate", "action_probs", "recurrent_out", "memory_size"]
-                    nodes += [scope + x for x in node_list]
+                if self.trainers[brain_name].parameters["use_recurrent"]:
+                    nodes += [scope + x for x in ["recurrent_out", "memory_size"]]
         if len(scopes) > 1:
             self.logger.info("List of available scopes :")
             for scope in scopes: