Reinforcement Learning in Agent-Based Market Simulation: Unveiling Realistic Stylized Facts and Behavior
By Zhiyuan Yao, Zheng Li, Matthew Thomas, Ionut Florescu
Rating
1383
Battle Count: 96
Relevance
9/10
Highly relevant for understanding market microstructure and developing realistic simulations for testing trading strategies
Implementation Complexity
7/10
Requires implementation of reinforcement learning agents and a realistic market simulation environment
Reproducibility
4/5
Detailed methodology and simulation setup provided, but exact hyperparameters and random seeds not specified
About this paper
Methodology: Reinforcement Learning in Agent-Based Simulation. Problem types: Market Making, Algorithmic Execution, Market Simulation.
The interactive Everscope explorer (charts, battles, favorites) loads below.