ddqn.py 文件源码

def eps_greedy(self, state, exploration_rate):
        prop = np.random.uniform()
        q_max = None
        q_min = None
        if prop < exploration_rate:
            # Select a random action
            action_index = np.random.randint(0, len(config.ale_actions))
        else:
            # Select a greedy action
            state = Variable(state)
            if config.use_gpu:
                state.to_gpu()
            q = self.compute_q_variable(state, test=True)
            if config.use_gpu:
                action_index = cuda.to_cpu(cuda.cupy.argmax(q.data))
                q_max = cuda.to_cpu(cuda.cupy.max(q.data))
                q_min = cuda.to_cpu(cuda.cupy.min(q.data))
            else:
                action_index = np.argmax(q.data)
                q_max = np.max(q.data)
                q_min = np.min(q.data)

        action = self.get_action_with_index(action_index)
        # No-op
        self.no_op_count = self.no_op_count + 1 if action == 0 else 0
        if self.no_op_count > config.rl_no_op_max:
            no_op_index = np.argmin(np.asarray(config.ale_actions))
            actions_without_no_op = []
            for i in range(len(config.ale_actions)):
                if i == no_op_index:
                    continue
                actions_without_no_op.append(config.ale_actions[i])
            action_index = np.random.randint(0, len(actions_without_no_op))
            action = actions_without_no_op[action_index]
            print "Reached no_op_max.", "New action:", action

        return action, q_max, q_min