1 result found Sort:

ChuaCheowHuan
gym-continuousDoubleAuction ChuaCheowHuan
31
142
mit
7
A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.
ppo ray lstm marl rllib n-player zero-sum self-play double-auction zero-sum-games gym-environment limit-order-book quantitative-finance quantitative-trading financial-engineering market-microstructure high-frequency-trading multi-agent-reinforcement-learning
Created 2019-07-20
309 commits to master branch, last one 4 years ago