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.
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.