Research map / Reinforcement learning / Offline RL
Reinforcement-Learning Based Portfolio Management with Augmented Asset Movement Prediction States
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 |
|---|---|---|---|
| Augment asset-price states with movement-prediction labels | DPM on Bitcoin · Bitcoin | Portfolio Value: 140.9% | Helped |
| Augment asset-price states with news-derived movement representations | DPM on HighTech · HighTech | Portfolio Value: 15.7% | Helped |
| Augment states with movement-prediction information | DPM on Bitcoin · Bitcoin | Sharpe Ratio: 11.73% | Helped |
| Augment states with movement-prediction information | DPM on HighTech · HighTech | Sharpe Ratio: 40.45% | Helped |
| Use movement predictions with accuracy above 60% | DPM on Bitcoin and HighTech · Bitcoin and HighTech simulations | Portfolio Value: 60% | Helped |
| Use sparse movement labels with 50% density and 70% accuracy | DPM on Bitcoin · Bitcoin simulation | Portfolio Value: 90.3% | Helped |
| Increase movement-label density | SARL on Bitcoin · Bitcoin simulation | Portfolio Value | Helped |
| Use financial-news embeddings instead of random labels at similar prediction accuracy | SARL on HighTech · HighTech simulation | Portfolio Value | Helped |
| Use SARL with PG or PPO rather than DPM | RL-based portfolio management · Bitcoin and HighTech | Sharpe Ratio | Mixed |
Closest papers by meaning
- Augmented Lagrangian Risk-constrained Reinforcement Learning for Portfolio Optimization (Student Abstract) (AAAI 2025 · similarity 0.88)
- Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets (NeurIPS 2025 · similarity 0.87)
- AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning (ICML 2025 · similarity 0.87)
- Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios (NeurIPS 2026 · similarity 0.86)
- Latent Variable Estimation in Bayesian Black-Litterman Models (ICML 2025 · similarity 0.85)
- Towards Financial World Modeling (NeurIPS 2026 · similarity 0.85)
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.