This is the last part of the research paper “Reinforcement Learning In Agent-based Market Simulation: Unveiling Realistic Stylized Facts And Behavior”. Use the table of links below to navigate to the next part.
Table of Links
Part 1: Abstract & Introduction
Part 4: Agents & Simulation Details
Part 8: Market and Agent Responsiveness to External Events
Part 9: Conclusion & References
Part 10: Additional Simulation Results
Part 11: Simulation Configuration
7.2 Simulation Configuration
Table 2 consists of all 14 agents’ configurations for groups of training, testing, and untrained. The hyper-parameters can be referenced in section 3.2.
Table 3 describes the detailed setups for the special simulations mentioned in Section 5.2 (Flash Sale and Informed LTs).
Table 4 shows the market characteristics of the simulations generated from different sets of hyper-parameters.
Table 5 shows the different setups for the simulation results.
Authors:
(1) Zhiyuan Yao, Stevens Institute of Technology, Hoboken, New Jersey, USA ([email protected]);
(2) Zheng Li, Stevens Institute of Technology, Hoboken, New Jersey, USA ([email protected]);
(3) Matthew Thomas, Stevens Institute of Technology, Hoboken, New Jersey, USA ([email protected]);
(4) Ionut Florescu, Stevens Institute of Technology, Hoboken, New Jersey, USA ([email protected]).
This paper is available on arxiv under CC BY-NC-SA 4.0 DEED license.