mwalton / ToM-hanabi-neurips19

Implementation of nested theory of mind belief estimation & implicit communication intrinsic rewards.

Hanabi ToM

Implementation of nested theory of mind belief estimation & implicit communication intrinsic rewards proposed in Theory of Mind for Deep Reinforcement Learning in Hanabi

Citation

@misc{fuchs2019theory,
      title={Theory of Mind for Deep Reinforcement Learning in Hanabi}, 
      author={Andrew Fuchs and Michael Walton and Theresa Chadwick and Doug Lange},
      year={2019},
      eprint={2101.09328},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}