This dissertation focuses on monetary policy in a dynamic general equilibrium open economy under an adaptive learning framework. The policymakers thus should consider undo this additional distortion that of imperfect knowledge. It contains three chapters. The first chapter, motivated by Japan's economic experiences and policy debates over the past two decades, examines the volatility and welfare impact of alternative monetary policy. I first show that a learning process and associated forecast errors induce higher volatility in the economy. In particular, explicit exchange rate stabilization is unwarranted. Contrary to results based on rational expectations, I show that even though highly inflation-sensitive rules do raise output volatility, they may nevertheless improve overall welfare under learning setting by smoothing inflation fluctuations. Chapter 2 studies one salient policy debate on monetary policy design in an open economy; namely, whether, and under what conditions, the policymakers should target domestic producer price inflation versus consumer price inflation. The main finding is that under learning dynamics the relative size of shocks can alter a preferred policy choice. Using a longer length of historical data to update expectations helps provide better information in the learning process and improve policy performance. In Chapter 3, I investigate monetary policy design with a non-trivial policy tradeoff under rational expectations. I find that when the policymakers face this policy tradeoff the dominant source of shocks can alter a preferred policy rule.