Devcon VI

Parameter Optimization and Emergent Behavior in DeFi: Agent Based Simulations and Reinforcement Learning
10-12, 13:00–15:00 (America/Bogota), Workshop 3

As in any complex system there may be emergent behaviors in DeFi protocols. In this workshop we will show the basics of how agent based simulations combined with reinforcement learning can be used to explore these and also for optimization of various protocol parameter values.

This will be based on https://github.com/vegaprotocol/vega-market-sim and https://github.com/msabvid/cpm_agent_based_sim . Ideally, try to follow setup in Vega-market-sim beforehand, but we'll go through it together.

I am currently a Head of Research at Vega protocol and Associate Professor of Mathematics at the University of Edinburgh. I've been interested in programming from an early age, oscillating between applied problems (coding) and theoretical (mathematics). At Vega I am mainly focused on whole system modelling, design validation and development of new protocol features. My maths research is on the theoretical aspects of reinforcement learning and optimal control algorithms.