2 code implementations • 17 Jan 2023 • David W. Zhang, Corrado Rainone, Markus Peschl, Roberto Bondesan
Finding the best way to schedule operations in a computation graph is a classical NP-hard problem which is central to compiler optimization.
1 code implementation • 30 Dec 2021 • Markus Peschl, Arkady Zgonnikov, Frans A. Oliehoek, Luciano C. Siebert
Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions.