no code implementations • 9 Oct 2019 • Hao-Ran Wei, Yuanbo Wang, Lidia Mangu, Keith Decker
We build a profitable electronic trading agent with Reinforcement Learning that places buy and sell orders in the stock market.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 7 Oct 2019 • Kevin Corder, Manuel M. Vindiola, Keith Decker
Our approach augments the multi-agent actor-critic method's centralized training phase with generative modeling so that agents may infer other agents' observations when provided with locally available context.