RL-for-trading research divides by problem structure, and the division predicts credibility: execution and hedging (dense feedback, clear costs) produce results that replicate; end-to-end portfolio alpha (sparse feedback, non-stationary environment) produces the field’s most spectacular simulator victories. The map below follows that gradient — read every branch with the environment-audit checklist.
flowchart TD ROOT["Reinforcement Learning for Trading<br>331 papers"] ROOT --> S0["Portfolio & allocation RL<br>147 papers"] ROOT --> S1["Execution RL<br>30 papers"] ROOT --> S2["Market-making RL<br>15 papers"] ROOT --> S3["Hedging RL<br>33 papers"] ROOT --> S4["Methods & training<br>60 papers"]
331 papers mapped · ranked by rigor-weighted score · regenerated automatically as the daily pipeline scores new papers.
Portfolio & allocation RL
End-to-end policies from prices to weights — the ambitious branch.
- Advancing Algorithmic Trading: A Multi-Technique Enhancement of Deep Q-Network Models — Holy Grail, rigor 9.0
- Optimizing Portfolio with Two-Sided Transactions and Lending: A Reinforcement Learning Framework — Holy Grail, rigor 9.0
- AlphaPortfolio: Direct Construction Through Deep Reinforcement Learning and Interpretable AI — Holy Grail, rigor 9.0
- Data-Driven Dynamic Portfolio Selection with Vine Copula Simulation and Reinforcement Learning — Holy Grail, rigor 8.0
- FR-LUX: Friction-Aware, Regime-Conditioned Policy Optimization for Implementable Portfolio Management — Holy Grail, rigor 8.0
- Distributionally Robust Deep Q-Learning — Holy Grail, rigor 7.5
- …and 141 more in the portfolio & allocation rl area
Execution RL
Order placement and scheduling — the credible branch.
- Minimal Batch Adaptive Learning Policy Engine for Real-Time Mid-Price Forecasting in High-Frequency Trading — Holy Grail, rigor 8.5
- Learning Market Making with Closing Auctions — Holy Grail, rigor 8.0
- Optimal Execution with Reinforcement Learning — Holy Grail, rigor 8.0
- What Teaches Robots to Walk, Teaches Them to Trade too – Regime Adaptive Execution using Informed Data and LLMs — Holy Grail, rigor 8.0
- Event-Based Limit Order Book Simulation under a Neural Hawkes Process: Application in Market-Making — Holy Grail, rigor 7.0
- RL-Exec: Impact-Aware Reinforcement Learning for Opportunistic Optimal Liquidation, Outperforms TWAP and a Book-Liquidity VWAP on BTC-USD Replays — Holy Grail, rigor 8.5
- …and 24 more in the execution rl area
Market-making RL
Learned quoting under inventory and adverse selection.
- Improving DeFi Accessibility through Efficient Liquidity Provisioning with Deep Reinforcement Learning — Holy Grail, rigor 8.0
- Reinforcement Learning with Hawkes-Structured Networks for Market Making — Holy Grail, rigor 7.0
- Reinforcement Learning in High-frequency Market Making — Holy Grail, rigor 6.0
- Exploiting Risk-Aversion and Size-dependent fees in FX Trading with Fitted Natural Actor-Critic — Holy Grail, rigor 6.0
- Robust Market Making: To Quote, or not To Quote — Holy Grail, rigor 6.0
- IMM: An Imitative Reinforcement Learning Approach with Predictive Representation Learning for Automatic Market Making — Holy Grail, rigor 6.0
- …and 9 more in the market-making rl area
Hedging RL
Deep hedging under costs — the second credible branch.
- Application of Deep Reinforcement Learning to At-the-Money S&P 500 Options Hedging — Holy Grail, rigor 7.5
- Stochastic Policy Gradient Methods in the Uncertain Volatility Model — Holy Grail, rigor 7.5
- Deeper Hedging: A New Agent-based Model for Effective Deep Hedging — Holy Grail, rigor 7.5
- Deep Hedging with Reinforcement Learning: A Practical Framework for Option Risk Management — Holy Grail, rigor 8.5
- Enhancing Deep Hedging of Options with Implied Volatility Surface Feedback Information — Holy Grail, rigor 7.5
- A Risk Sensitive Contract-unified Reinforcement Learning Approach for Option Hedging — Holy Grail, rigor 8.5
- …and 27 more in the hedging rl area
Methods & training
Algorithms, sample efficiency, and environment design.
- Integrating Large Language Models and Reinforcement Learning for Sentiment-Driven Quantitative Trading — Holy Grail, rigor 8.5
- Interpretable Hypothesis-Driven Trading:A Rigorous Walk-Forward Validation Framework for Market Microstructure Signals — Holy Grail, rigor 9.0
- Harnessing Deep Q-Learning for Enhanced Statistical Arbitrage in High-Frequency Trading: A Comprehensive Exploration — Holy Grail, rigor 7.5
- Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models — Holy Grail, rigor 8.5
- Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation — Holy Grail, rigor 8.0
- AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery — Holy Grail, rigor 8.0
- …and 54 more in the methods & training area
Evaluation lens for this field: see the guides index · Full hub: /topics/reinforcement-learning/