52eb159f696e9cd810072c3a2cc350ae8843f707,agents/dfp_agent.py,DFPAgent,learn_from_batch,#DFPAgent#Any#,29

Before Change

        // create the inputs for the network
        input = current_states
        input.append(np.repeat(np.expand_dims(self.current_goal, 0), self.tp.batch_size, 0))

        // get the current outputs of the network
        targets = self.main_network.online_network.predict(input)

After Change

        // create the inputs for the network
        input = current_states
        input["goal"] = np.repeat(np.expand_dims(self.current_goal, 0), self.tp.batch_size, 0)

        // get the current outputs of the network
        targets = self.main_network.online_network.predict(input)

Instances