Recent Developments in Machine Learning Methods for Stochastic Control and Games

Hu, Ruimeng; Laurière, Mathieu

doi:10.2139/ssrn.4096569

SSRN Journal

2022

DOI: 10.2139/ssrn.4096569

|View full text |Cite

Recent Developments in Machine Learning Methods for Stochastic Control and Games

Ruimeng Hu

Mathieu Laurière

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

Publication Types

Select...

Article4

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

(1 citation statement)

References 191 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also has become an appealing alternative in several financial decision making problems, where one wishes to learn optimal strategies with no explicit assumptions about the environment. For a thorough survey of recent advances in RL applied to financial problems, see, e.g., [25,29,27].…”

mentioning

confidence: 99%

Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning

Coache,

Jaimungal,

Cartea

2023

SIAM J. Finan. Math.

View full text Add to dashboard Cite

We propose a novel framework to solve risk-sensitive reinforcement learning problems where the agent optimizes time-consistent dynamic spectral risk measures. Based on the notion of conditional elicitability, our methodology constructs (strictly consistent) scoring functions that are used as penalizers in the estimation procedure. Our contribution is threefold: we (i) devise an efficient approach to estimate a class of dynamic spectral risk measures with deep neural networks, (ii) prove that these dynamic spectral risk measures may be approximated to any arbitrary accuracy using deep neural networks, and (iii) develop a risk-sensitive actor-critic algorithm that uses full episodes and does not require any additional nested transitions. We compare our conceptually improved reinforcement learning algorithm with the nested simulation approach and illustrate its performance in two settings: statistical arbitrage and portfolio allocation on both simulated and real data.

show abstract

mentioning

confidence: 99%

Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning

Coache,

Jaimungal,

Cartea

2023

SIAM J. Finan. Math.

View full text Add to dashboard Cite

show abstract

Optimal bailout strategies resulting from the drift controlled supercooled Stefan problem

Cuchiero¹,

Reisinger

Rigger³

2023

Ann Oper Res

View full text Add to dashboard Cite

We consider the problem faced by a central bank which bails out distressed financial institutions that pose systemic risk to the banking sector. In a structural default model with mutual obligations, the central agent seeks to inject a minimum amount of cash in order to limit defaults to a given proportion of entities. We prove that the value of the central agent’s control problem converges as the number of defaultable institutions goes to infinity, and that it satisfies a drift controlled version of the supercooled Stefan problem. We compute optimal strategies in feedback form by solving numerically a regularized version of the corresponding mean field control problem using a policy gradient method. Our simulations show that the central agent’s optimal strategy is to subsidise banks whose equity values lie in a non-trivial time-dependent region.

show abstract

Recent advances in modeling and control of epidemics using a mean field approach

Roy,

Singh,

Narahari

2023

Sādhanā

View full text Add to dashboard Cite

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Recent Developments in Machine Learning Methods for Stochastic Control and Games

Cited by 4 publications

References 191 publications

Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning

Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning

Optimal bailout strategies resulting from the drift controlled supercooled Stefan problem

Recent advances in modeling and control of epidemics using a mean field approach

Contact Info

Product

Resources

About