Enhancing Reinforcement Learning-Based Crypto Asset Trading: Focusing on the Korean Venue Share Indicator

Crypto asset markets are often described as globally integrated. However, empirical evidence suggests that they remain segmented across exchanges and jurisdictions. One notable example is the Korean premium (i.e., Kimchi premium), which refers to persistent price gaps between Korean exchanges and offshore venues. The Korean market accounts for a substantial share of global crypto trading activity. Therefore, this segmentation can affect price discovery and create opportunities for systematic trading. Motivated by the Korean premium, this study introduces the Korean Venue Share Indicator (KVSI). Based on the price discovery literature, KVSI is an interpretable venue-level indicator that uses the relative trading volume share between Korean and global exchanges. This study integrates KVSI into the state space of multiple reinforcement learning algorithms to evaluate whether venue-level information improves trading decisions. The results show that the proposed model with KVSI achieves statistically significant improvements in cumulative return (CR), Sharpe ratio (SR), and maximum drawdown (MDD) compared to the baseline model without KVSI. It also achieves higher CR and mixed effects on risk metrics (SR, MDD) relative to benchmark strategies. Additional analyses indicate that the performance gains from KVSI are market-regime-dependent. Overall, the findings have practical implications for developing cross-market systematic trading strategies by leveraging a venue-level indicator as a proxy for market segmentation.