Modelling crypto markets by multi-agent reinforcement learning
By Johann Lussange, Stefano Vrizzi, Stefano Palminteri, Boris Gutkin
Rating
1492
Battle Count: 35
Relevance
8/10
Highly relevant for understanding crypto market dynamics and developing trading strategies, but limitations in strategy complexity
Implementation Complexity
7/10
Requires understanding of reinforcement learning and financial modeling, but code is provided
Reproducibility
4/5
Code repository provided, detailed model description, but specific data may not be publicly available
About this paper
Methodology: Multi-agent reinforcement learning. Problem types: Time Series Forecasting, Market Making, Reinforcement Learning.
The interactive Everscope explorer (charts, battles, favorites) loads below.