使用增強式學習法改善一個簡易的臺灣股價指數期貨當沖交易系統

Abstract

本論文應用增強式學習法中的Q-learning於改善一個簡易的臺灣股價指數期貨當沖交易系統，使用歷史資料模擬原本策略的績效，以及訓練與檢測改善後的績效。 研究標的為臺灣股價指數期貨(以下簡稱臺股期貨)，訓練資料為2003年到2007年每個交易日的每筆成交資訊，檢測期間為2008年1月到2009年5月。 被改善的策略為一作順勢交易的通道突破系統，增強式學習法的訓練結果用以判斷每次交易是否該改作逆勢交易，以期取得較大的獲利機會。

This thesis applied Q-learning algorithm of reinforcement learning to improve a simple intra-day trading system of Taiwan stock index future. We simulate the performance of the original strategy by back-testing it with historical data. Furthermore, we use historical information as training data for reinforcement learning and examine the improved achievement. The training data are the tick data of every trading day from 2003 to 2007 and the testing period is from January 2008 to May 2009. The original strategy is a trend-following channel breakout system. We take the result of reinforcement learning to determine whether to do trend following or countertrend trading every time the system plans to make position.