Code for Optimal stopping using distributional reinforcement learning. Includes our implementation of DDQN, C51 and IQN. Also includes the implementation of the binomial model and all other benchmarks that appear in the paper. We also include our data set for the real S&P500 stock data experiment and code to generate the geometric Brownian motion data set.
For more details, please read the full paper: Deep Reinforcement Learning for Optimal Stopping with application in Financial Engineering.