2021

  • Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning
    Zhang-Wei Hong, Prabhat Nagarajan, and Guilherme J. Maeda
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD). September 2021.
  • Reconnaissance for Reinforcement Learning with Safety Constraints
    Shin-ichi Maeda, Hayato Watahiki, Yi Ouyang, Shintaro Okada, Masanori Koyama, and Prabhat Nagarajan European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD). September 2021.
  • ChainerRL: A Deep Reinforcement Learning Library
    Yasuhiro Fujita, Prabhat Nagarajan, Toshiki Kataoka, Takahiro Ishikawa
    Journal of Machine Learning Research (JMLR). 22(77):1−14, April 2021.


2020

  • Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators
    Yasuhiro Fujita, Kota Uenishi, Avinash Ummadisingu, Prabhat Nagarajan, Shimpei Masuda, Mario Ynocente Castro
    International Conference on Intelligent Robots and Systems (IROS 2020) October 2020.


2019

  • Learning Latent State Spaces for Planning through Reward Prediction
    Aaron Havens, Yi Ouyang, Prabhat Nagarajan, Yasuhiro Fujita
    Workshop on Deep Reinforcement Learning at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) December 2019.

  • Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
    Daniel S. Brown, Wonjoon Goo, Prabhat Nagarajan, Scott Niekum
    International Conference on Machine Learning (ICML) June 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.