Research map / Reinforcement learning / Policy gradient and actor-critic
DeepTrader: A Deep Reinforcement Learning Approach for Risk-Return Balanced Portfolio Management with Market Conditions Embedding
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add the market scoring unit to dynamically adjust long/short allocation (ablation) | DeepTrader · DJIA and HSI | ASR: 0.638 -> 0.718 (DJIA); 0.930 -> 1.044 (HSI) | Helped |
| Add the market scoring unit to dynamically adjust long/short allocation (ablation) | DeepTrader · DJIA and HSI | MDD (%): 31.24 -> 22.61 (DJIA); 20.17 -> 17.11 (HSI) | Helped |
| Add spatial attention and graph convolution for cross-stock relations (ablation) | DeepTrader · DJIA and HSI | ASR: 0.628 -> 0.718 (DJIA); 0.902 -> 1.044 (HSI) | Helped |
| Add spatial attention and graph convolution for cross-stock relations (ablation) | DeepTrader · DJIA and HSI | MDD (%): 26.33 -> 22.61 (DJIA); 19.93 -> 17.11 (HSI) | Helped |
| Use negative maximum drawdown instead of rate of return as the market-unit reward (ablation) | DeepTrader · DJIA | MDD (%): 45.52 -> 22.61 | Helped |
| Use negative maximum drawdown instead of Sharpe ratio as the market-unit reward (ablation) | DeepTrader · DJIA | MDD (%): 46.06 -> 22.61 | Helped |
| Use negative maximum drawdown instead of Calmar ratio as the market-unit reward (ablation) | DeepTrader · DJIA | MDD (%): 31.10 -> 22.61 | Helped |
| Use rate of return instead of maximum drawdown as the market-unit reward (ablation) | DeepTrader · DJIA | ARR (%): 12.35 -> 15.60 | Helped |
| Use Sharpe ratio instead of maximum drawdown as the market-unit reward (ablation) | DeepTrader · DJIA | ARR (%): 12.35 -> 14.36 | Helped |
| Use Sharpe ratio as the market-unit reward (ablation) | DeepTrader · DJIA | ASR: 0.718 -> 0.700 | Hurt |
| Use a learned causal graph rather than industry classification (ablation) | DeepTrader graph convolution · DJIA | ASR: 0.718 -> 0.750 | Helped |
| Use a learned causal graph rather than industry classification (ablation) | DeepTrader graph convolution · HSI | MDD (%): 17.11 -> 15.90 | Helped |
Closest papers by meaning
- Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning (AAAI 2025 · similarity 0.85)
- Augmented Lagrangian Risk-constrained Reinforcement Learning for Portfolio Optimization (Student Abstract) (AAAI 2025 · similarity 0.85)
- EarnHFT: Efficient Hierarchical Reinforcement Learning for High Frequency Trading (AAAI 2024 · similarity 0.84)
- Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios (NeurIPS 2026 · similarity 0.84)
- Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking (NeurIPS 2025 · similarity 0.84)
- DHMoE: Diffusion Generated Hierarchical Multi-Granular Expertise for Stock Prediction (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.