## Feedback on Related Work SOTA ### Current Assessment Your related work section provides a foundational overview of the intersection between deep reinforcement learning (DRL) and portfolio management. However, it currently lacks depth and critical analysis, which are essential for establishing the context and significance of your research. The references to Jiang et al. (2017) and Liu et al. (2021) are a good start but need to be more thoroughly analyzed to demonstrate how they relate to your proposed method. ### Specific Improvements Needed 1. **Depth of Analysis**: Expand on the methodologies and findings of the cited studies. For example, when discussing Jiang et al. (2017), consider elaborating on their approach to DRL in portfolio management and how it compares to your regime-aware framework. Similarly, analyze Liu et al. (2021) in terms of their contributions and limitations. This will help clarify how your work builds upon or diverges from existing literature. 2. **Inclusion of Recent Literature**: Incorporate discussions of key recent papers that are pertinent to your work, particularly those highlighted by your instructor. These include: - **"Adaptive Portfolio Management in Volatile Markets Using Deep Reinforcement Learning" (2025)**, which discusses DRL applications in volatile conditions. - **"A Comparative Analysis of Deep Reinforcement Learning Techniques in Portfolio Optimization for Global Market Indexes" (2024)**, which provides insights into various DRL techniques that could inform your methodology. - **"Deep Reinforcement Learning for Investor-Specific Portfolio Optimization: A Volatility-Guided Asset Selection Approach" (2025)**, which could provide a unique perspective on tailoring strategies to individual investor profiles. - **"Dynamic Portfolio Optimization with Deep Reinforcement Learning: Empirical Insights from Indian Capital Markets" (2025)**, which offers empirical evidence that may support your findings. - **"Enhanced Investment Decision Making with a Reinforcement Learning-Based Multi-Agent Portfolio Management System" (2024)**, which explores multi-agent systems that could complement your approach. - **"SAMP-HDRL: Segmented Allocation with Momentum-Adjusted Utility for Multi-agent Portfolio Management via Hierarchical Deep Reinforcement Learning" (2025)**, which may provide insights into hierarchical approaches that could enhance your framework. - **"Portfolio Optimization System (POS): A Deep Reinforcement Learning Approach for Market-Adaptive Investment Strategies" (2025)**, which discusses adaptive strategies in portfolio management. 3. **Articulation of Novelty**: Clearly articulate how your proposed framework improves upon existing methods. Detail the specific enhancements in methodology and outcomes compared to those in the literature. This will strengthen your argument for the novelty of your work. ### Concrete Next Steps 1. **Revise the Related Work Section**: Incorporate a critical analysis of Jiang et al. (2017) and Liu et al. (2021), explicitly connecting their methodologies to your proposed method. This should include a discussion of their findings and how they inform your research. 2. **Integrate Recent Studies**: Add discussions of the recent papers mentioned above, focusing on their methodologies and findings. This will enhance the depth of your literature review and demonstrate your awareness of the current state of research. 3. **Clarify Novelty**: Revisit your contribution section to clearly articulate how your work builds upon and improves existing literature. This should include specific methodological advancements and expected outcomes. ### Overall Assessment **Partial**: Your related work section lays a good foundation but requires significant enhancements in depth, credibility, and critical analysis to effectively support your research. Addressing these gaps will strengthen the overall quality of your thesis and its contribution to the field of dynamic portfolio management. Please implement these suggestions and update your related work section accordingly. Let me know when you have made these revisions! --- This feedback is for the **📚 Related Work & SOTA** stage. Please address the feedback and update your work accordingly.