indylab/nxdo

Deep RL Code for XDO: A Double Oracle Algorithm for Extensive-Form Games

Code for XDO: A Double Oracle Algorithm for Extensive-Form Games

Includes RLlib PyTorch implementations of NXDO, PSRO, and NFSP.

1. Installation
2. Running Experiments

Check this repo for tabular experiment code.

Feel free to reach out to JB for help at jblanier@uci.edu!