What is the Value of the Cross-Sectional Approach to Deep Reinforcement Learning?

Aboussalah, Amine Mohamed; Xu, Ziyun; Lee, Chi-Guhn

doi:10.2139/ssrn.3748130

Cited by 2 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RL Approach. Both value-based methods such as Q-learning [60,166], SARSA [166], and DQN [163], and policy-based algorithms such as DPG and DDPG [224,110,236,137,3] have been applied to solve portfolio optimization problems. The state variables are often composed of time, asset prices, asset past returns, current holdings of assets, and remaining balance.…”

Section: The Covariance Matrix Is Denoted Bymentioning

confidence: 99%

“…The benchmark strategies include Constantly Rebalanced Portfolio (CRP) [236,110] where at each period the portfolio is rebalanced to the initial wealth distribution among the assets, and the buyand-hold or do-nothing strategy [163,3] which does not take any action but rather holds the initial portfolio until the end. The performance measures studied in these papers include the Sharpe ratio [236,211,224,110,137,163,208], the Sortino ratio [236], portfolio returns [208,224,137,163,236,3], portfolio values [110,224,166], and cumulative profits [60]. Some models incorporate the transaction costs [110,137,60,163,236,3] and investments in the risk-free asset [236,211,208,60,110].…”

Section: The Covariance Matrix Is Denoted Bymentioning

confidence: 99%

“…The performance measures studied in these papers include the Sharpe ratio [236,211,224,110,137,163,208], the Sortino ratio [236], portfolio returns [208,224,137,163,236,3], portfolio values [110,224,166], and cumulative profits [60]. Some models incorporate the transaction costs [110,137,60,163,236,3] and investments in the risk-free asset [236,211,208,60,110].…”

Section: The Covariance Matrix Is Denoted Bymentioning

confidence: 99%

“…The model outperforms the benchmark CRP and the model considered in [110] in terms of several performance measures including Sharpe ratio and Sortino ratio. Using Actor-Critic methods, [3] combined the mean-variance framework (the actor determines the policy using the mean-variance framework) and the Kelly Criterion framework (the critic evaluates the policy using their growth rate). They studied eight policy-based algorithms including DPG, DDPG, and PPO, among which DPG was shown to achieve the best performance.…”

Section: The Covariance Matrix Is Denoted Bymentioning

confidence: 99%

See 3 more Smart Citations

Recent Advances in Reinforcement Learning in Finance

Hambly,

Xu,

Yang

2021

Preprint

View full text Add to dashboard Cite

The rapid changes in the finance industry due to the increasing amount of data have revolutionized the techniques on data processing and data analysis and brought new theoretical and computational challenges. In contrast to classical stochastic control theory and other analytical approaches for solving financial decision-making problems that heavily reply on model assumptions, new developments from reinforcement learning (RL) are able to make full use of the large amount of financial data with fewer model assumptions and to improve decisions in complex financial environments. This survey paper aims to review the recent developments and use of RL approaches in finance. We give an introduction to Markov decision processes, which is the setting for many of the commonly used RL approaches. Various algorithms are then introduced with a focus on value and policy based methods that do not require any model assumptions. Connections are made with neural networks to extend the framework to encompass deep RL algorithms. Our survey concludes by discussing the application of these RL algorithms in a variety of decision-making problems in finance, including optimal execution, portfolio optimization, option pricing and hedging, market making, smart order routing, and robo-advising.

show abstract