Benchmarking Robustness of Deep Reinforcement Learning approaches to Online Portfolio Management

ArXiv ID: 2306.10950 “View on arXiv”

Authors: Unknown

Abstract

Deep Reinforcement Learning approaches to Online Portfolio Selection have grown in popularity in recent years. The sensitive nature of training Reinforcement Learning agents implies a need for extensive efforts in market representation, behavior objectives, and training processes, which have often been lacking in previous works. We propose a training and evaluation process to assess the performance of classical DRL algorithms for portfolio management. We found that most Deep Reinforcement Learning algorithms were not robust, with strategies generalizing poorly and degrading quickly during backtesting.

Keywords: Deep Reinforcement Learning, Online Portfolio Selection, Backtesting, Market Representation, Strategy Generalization, Multi-Asset

Complexity vs Empirical Score

• Math Complexity: 7.5/10
• Empirical Rigor: 8.0/10
• Quadrant: Holy Grail
• Why: The paper employs advanced Deep Reinforcement Learning mathematics (Policy Gradients, MDPs, entropy regularization) and demonstrates high empirical rigor through a standardized benchmarking process, public data, open-source code, and robust statistical evaluation of DRL agents.

  flowchart TD
    A["Research Goal: Benchmark DRL Robustness in Online Portfolio Management"] --> B{"Methodology"}
    B --> C["Market Representation & Data Processing<br/>Multi-Asset Time Series"]
    B --> D["Algorithm Selection & Training<br/>Classical DRL Agents"]
    C --> E["Backtesting Process<br/>Out-of-sample Evaluation"]
    D --> E
    E --> F["Robustness Metrics<br/>Generalization & Degradation Analysis"]
    F --> G{"Key Findings / Outcomes"}
    G --> H["Most DRL algorithms lack robustness<br/>Strategies generalize poorly<br/>Performance degrades quickly"]