---
title: Trading with Deep Reinforcement Learning
url: https://www.ml-quant.com/papers/repec/gam-jdataj-v-6-y-2021-i-11-p-119-d-680602/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:gam:jdataj:v:6:y:2021:i:11:p:119-:d:680602
source_url: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.mdpi.com%2F2306-5729%2F6%2F11%2F119%2Fpdf%3Bh%3Drepec%3Agam%3Ajdataj%3Av%3A6%3Ay%3A2021%3Ai%3A11%3Ap%3A119-%3Ad%3A680602
featured: 2023-06-14
citations: unknown
topic: Trading, Microstructure & Execution
---


# Trading with Deep Reinforcement Learning

Deep reinforcement learning applied to trading on financial markets is discussed, including common structures, issues, and limitations of such approaches, as well as state representations critical for success and efficiency.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.mdpi.com%2F2306-5729%2F6%2F11%2F119%2Fpdf%3Bh%3Drepec%3Agam%3Ajdataj%3Av%3A6%3Ay%3A2021%3Ai%3A11%3Ap%3A119-%3Ad%3A680602
- Identifier: RePEc:gam:jdataj:v:6:y:2021:i:11:p:119-:d:680602
- Released: 2021-07-13
- First featured: Quant Letter No. 4 (2023-06-14): https://www.ml-quant.com/issues/2023-06-14/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Trading, Microstructure & Execution

## Related

- [Deep Reinforcement Learning for Active High Frequency Trading](https://www.ml-quant.com/papers/arxiv/2101.07107/): A new Deep Reinforcement Learning framework has been developed for high frequency stock trading, showing potential for profitable long-term strategies.
- [Deep reinforcement trading with predictable returns](https://www.ml-quant.com/papers/arxiv/2104.14683/): The performance of model-free deep reinforcement learning traders in a market environment with different mean-reverting factors is investigated.
- [An adaptive dual-level reinforcement learning approach for optimal trade execution](https://www.ml-quant.com/papers/arxiv/2307.10649/): The research introduces a reinforcement learning strategy that accurately tracks the daily volume-weighted average price of stocks, using a dual-level architecture for better results.
- [JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading](https://www.ml-quant.com/papers/arxiv/2308.13289/): JAX-LOB: The paper introduces JAX-LOB, the first GPU-powered limit order book simulator capable of processing multiple books simultaneously, designed for efficient large-scale simulations of LOB dynamics for research, calibration, and reinforcement learning training.
- [Domain-adapted Learning and Imitation: DRL for Power Arbitrage](https://www.ml-quant.com/papers/arxiv/2301.08360/): Leveraging Expertise: A dual-agent reinforcement learning approach can optimize European power arbitrage trading, improving training convergence and performance, and tripling profit and loss.
- [Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents*](https://www.ml-quant.com/papers/arxiv/2309.14615/): A study has shown that a gray-box method can significantly reduce the profits of a Deep Reinforcement Learning-based trading agent, highlighting the need for stronger automated trading systems.