Preprints

  • Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
    Daniel S. Brown, Wonjoon Goo, Prabhat Nagarajan, Scott Niekum
    arXiv April 2019.


2019

  • Learning from Suboptimal Demonstrations: Inverse Reinforcement Learning from Ranked Observations
    Daniel S. Brown, Wonjoon Goo, Prabhat Nagarajan, Scott Niekum
    Proceedings of The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), Montréal, Québec, Canada. July 2019.

  • Deterministic Implementations for Reproducibility in Deep Reinforcement Learning
    Prabhat Nagarajan, Garrett Warnell, Peter Stone
    AAAI 2019 Workshop on Reproducible AI, Honolulu, Hawaii. January 2019.


2018

  • Nondeterminism as a Reproducibility Challenge for Deep Reinforcement Learning
    Prabhat Nagarajan
    Master's Thesis, The University of Texas at Austin, August 2018
    Committee: Peter Stone (Supervisor), Scott Niekum

  • The Impact of Nondeterminism on Reproducibility in Deep Reinforcement Learning
    Prabhat Nagarajan, Garrett Warnell, Peter Stone
    2nd Reproducibility in Machine Learning Workshop at ICML 2018, Stockholm, Sweden.