# Learning to simulate realistic limit order book markets from data as a World Agent

arXiv: https://arxiv.org/abs/2210.09897 · HTML: https://mlsanity.com/paper/2210.09897/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 26 Sep 2022.

## Builds on (most cited first, 8 of 8)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [NIPS 2016 Tutorial: Generative Adversarial Networks](https://mlsanity.com/paper/1701.00160/) (2016)
- [Get Real: Realism Metrics for Robust Limit Order Book Market Simulations](https://mlsanity.com/paper/1912.04941/) (2019)
- [Generating Realistic Stock Market Order Streams](https://mlsanity.com/paper/2006.04212/) (2020)
- [Towards Realistic Market Simulations: a Generative Adversarial Networks Approach](https://mlsanity.com/paper/2110.13287/) (2021)
- [How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation?](https://mlsanity.com/paper/1906.12010/) (2019)

## Built on by (most cited first, 27 of 27)

- [On the Constrained Time-Series Generation Problem](https://mlsanity.com/paper/2307.01717/) (2023)
- [Non-adversarial training of Neural SDEs with signature kernel scores](https://mlsanity.com/paper/2305.16274/) (2023)
- [MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model](https://mlsanity.com/paper/2409.07486/) (2024)
- [Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network](https://mlsanity.com/paper/2309.00638/) (2023)
- [Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness](https://mlsanity.com/paper/2306.12806/) (2023)
- [LLM-driven Imitation of Subrational Behavior : Illusion or Reality?](https://mlsanity.com/paper/2402.08755/) (2024)
- [LOB-Based Deep Learning Models for Stock Price Trend Prediction: A Benchmark Study](https://mlsanity.com/paper/2308.01915/) (2023)
- [From Deep Learning to LLMs: A survey of AI in Quantitative Investment](https://mlsanity.com/paper/2503.21422/) (2025)
- [Multi-Modal Financial Time-Series Retrieval Through Latent Space Projections](https://mlsanity.com/paper/2309.16741/) (2023)
- [K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs](https://mlsanity.com/paper/2302.11996/) (2023)
- [Simulating the Economic Impact of Rationality through Reinforcement Learning and Agent-Based Modelling](https://mlsanity.com/paper/2405.02161/) (2024)
- [Optimal Execution with Reinforcement Learning](https://mlsanity.com/paper/2411.06389/) (2024)
- [TRADES: Generating Realistic Market Simulations with Diffusion Models](https://mlsanity.com/paper/2502.07071/) (2025)
- [LOB-Bench: Benchmarking Generative AI for Finance -- an Application to Limit Order Book Data](https://mlsanity.com/paper/2502.09172/) (2025)
- [TLOB: A Novel Transformer Model with Dual Attention for Price Trend Prediction with Limit Order Book Data](https://mlsanity.com/paper/2502.15757/) (2025)
- [Asynchronous Deep Double Duelling Q-Learning for Trading-Signal Execution in Limit Order Book Markets](https://mlsanity.com/paper/2301.08688/) (2023)
- [Reinforcement Learning in Agent-Based Market Simulation: Unveiling Realistic Stylized Facts and Behavior](https://mlsanity.com/paper/2403.19781/) (2024)
- [Limited or Biased: Modeling Sub-Rational Human Investors in Financial Markets](https://mlsanity.com/paper/2210.08569/) (2022)
- [Right Place, Right Time: Market Simulation-based RL for Execution Optimisation](https://mlsanity.com/paper/2510.22206/) (2025)
- [Reinforcement Learning in Queue-Reactive Models: Application to Optimal Execution](https://mlsanity.com/paper/2511.15262/) (2025)
- [INTAGS: Interactive Agent-Guided Simulation](https://mlsanity.com/paper/2309.01784/) (2023)
- [Financial Wind Tunnel: A Retrieval-Augmented Market Simulator](https://mlsanity.com/paper/2503.17909/) (2025)
- [The Invisible Handshake: Persistent Overpricing by Adaptive Market Agents](https://mlsanity.com/paper/2510.15995/) (2025)
- [From Jumps to Signatures: a Generative Method for Temporal Point Processes](https://mlsanity.com/paper/2607.06652/) (2026)
- [FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching](https://mlsanity.com/paper/2608.13096/) (2026)
- [M3: A State-Event Generative Foundation Model for Market Microstructure Dynamics](https://mlsanity.com/paper/2608.19227/) (2026)
- [Repurposing Deep Limit Order Book Forecasting for Scenario-Conditioned Market Impact Modeling](https://mlsanity.com/paper/2609.16930/) (2026)

## Abstract (arXiv)

Multi-agent market simulators usually require careful calibration to emulate real markets, which includes the number and the type of agents. Poorly calibrated simulators can lead to misleading conclusions, potentially causing severe loss when employed by investment banks, hedge funds, and traders to study and evaluate trading strategies. In this paper, we propose a world model simulator that accurately emulates a limit order book market -- it requires no agent calibration but rather learns the simulated market behavior directly from historical data. Traditional approaches fail short to learn and calibrate trader population, as historical labeled data with details on each individual trader strategy is not publicly available. Our approach proposes to learn a unique "world" agent from historical data. It is intended to emulate the overall trader population, without the need of making assumptions about individual market agent strategies. We implement our world agent simulator models as a Conditional Generative Adversarial Network (CGAN), as well as a mixture of parametric distributions, and we compare our models against previous work. Qualitatively and quantitatively, we show that the proposed approaches consistently outperform previous work, providing more realism and responsiveness.