Arash Tavakoli

Arash Tavakoli

PhD Student in Reinforcement Learning

Imperial College London
1st Floor, Observatory Building
South Kensington, London SW7 2AZ

a.tavakoli [at]

twitter github linkedin google scholar



  • 2014 – 2016:
    • MSc in Computer Science
    • University of Southern California (USC), Los Angeles, California, USA
  • 2010 – 2014:
    • MEng in Electrical Engineering
    • University College London (UCL), London, UK
  • 2012 – 2013:
    • Exchange Student in Electrical and Computer Engineering
    • Georgia Institute of Technology (Georgia Tech), Atlanta, Georgia, USA

Representative Publications

  • Action Branching Architectures for Deep Reinforcement Learning
    Arash Tavakoli, Fabio Pardo, Petar Kormushev
    In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI)
    New Orleans, Louisiana, USA, 2018.
    [PDF | AAAI Library | arXiv | code]

  • Time Limits in Reinforcement Learning
    Fabio Pardo, Arash Tavakoli, Vitaly Levdik, Petar Kormushev
    In Proceedings of the 35th International Conference on Machine Learning (ICML)
    Stockholm, Sweden, 2018.
    [PDF | PMLR Library | arXiv | videos & code]