ABIDES: An Agent-Based Interactive Event Simulation Environment
ABIDES: Towards High-Fidelity Market Simulation for AI Research
We introduce the agent-based interactive discrete event simulation environment (abides), a high-fidelity market simulation environment designed from the ground up to support artificial intelligence (ai) agent research in market applications.The simulator enables the simulation of tens of thousands of trading agents interacting with an exchange agent to facilitate transactions.It supports configurable pairwise network latencies between each individual agent as well as the exchange.We introduce the design of the simulator and illustrate its use and configuration with sample code, validating the environment with example trading scenarios.The utility of the simulation is illustrated through experiments to develop a market impact model.We close with discussion of future experimental problems it can be used to explore, such as the development of ml-based trading algorithms.
