Reinforcement Learning in Economics and Finance

• Published in: Computational economics Vol. 62; no. 1; pp. 425 - 462
• Main Authors: Charpentier, Arthur, Élie, Romuald, Remlinger, Carl
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.06.2023; Springer; Springer Nature B.V
• Subjects: Action; Agents; Algorithms; Behavior problems; Behavioral/Experimental Economics; Computer Appl. in Social and Behavioral Sciences; Data mining; Deep learning; Distance learning; Economic Theory/Quantitative Economics/Mathematical Methods; Economics; Economics and Finance; Finance; Game theory; Learning; Long term; Machine learning; Management science; Mapping; Math Applications in Computer Science; Multi-armed bandit problems; Online education; Operations Research/Decision Theory; Optimal control; Reinforcement; Rewards; Regret; C41; C63; D40; C44; C54; C57; C68; Reinforcement learning; learning; C18; Sequential learning; Multi-armed bandits; Control; Machine learning; Rewards; Online-learning; Markov decision process; C90; Causality; D70; C70; D83; C61

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal rewards. As in online learning, the agent learns sequentially. As...