Reinforcement Learning (RL) - Frontier Ledger

Reinforcement Learning (RL)

20 articles on deep Q-networks, policy gradients, multi-agent systems, and RL applications in trading.

1

Deep Q-Networks for Adaptive Market-Making

2

Policy-Gradient Methods for Dynamic Asset Allocation

3

Reward Engineering: Balancing Alpha vs Transaction Costs

4

Safe RL: Constraining Drawdowns During Training

5

Multi-Agent RL for Order-Book Simulation and Strategy Testing

6

Imitation Learning from Historical Trades of Top Funds

7

Curriculum Learning: Training Agents Across Increasing Market Complexity

8

Off-Policy Evaluation Techniques in Financial RL

9

Meta-Learning Agents that Adapt to New Symbols Quickly

10

Variance Reduction Tricks for Faster Convergence in Noisy Environments

11

Hierarchical RL for Multi-Horizon Portfolio Decisions

12

Using RLlib vs Stable-Baselines3—Toolkit Comparison

13

Case Study: RL-Powered Execution Algorithms vs VWAP Benchmarks

14

Option Delta-Hedging with Continuous-Time RL

15

Combining RL with Scenario Trees for Stress-Testing Portfolios

16

Interpreting RL Policies: SHAP for Q-Functions

17

Distributional RL to Model Tail-Risk Preferences

18

Sim-to-Real Transfer: Training Agents on Synthetic Order Books

19

Measuring Sample Efficiency in Tick-Level RL

20

Robustness of RL Strategies During Flash Crashes