Improved Policy Extraction via Online Q-Value Distillation.

Aman Jhunjhunwala Jaeyoung Lee Sean Sedwards Vahdat Abdelzad Krzysztof Czarnecki

Published in: IJCNN (2020)

Keyphrases

online learning
real time
information extraction
automatic extraction
search algorithm
decision making
online algorithms
information systems
lower bound
optimal policy
improved algorithm
state dependent
online environment