Action Branching Architectures for Deep Reinforcement Learning

Arash Tavakoli, Fabio Pardo, Petar Kormushev

References:

Arash Tavakoli, Fabio Pardo, Petar Kormushev, “Action Branching Architectures for Deep Reinforcement Learning”, In Proc. 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans, USA, 2018.

Bibtex Entry:

@inproceedings{tavakoli2018aaai,
  title={Action Branching Architectures for Deep Reinforcement Learning},
  author={Tavakoli, Arash and Pardo, Fabio and Kormushev, Petar},
  booktitle={Proc. 32nd AAAI Conference on Artificial Intelligence (AAAI 2018)},
  year={2018},
  month={February},
  address={New Orleans, USA},
  url = "https://kormushev.com/papers/Tavakoli_AAAI-2018.pdf"
}

PDF Preview: