2023
MEET: A Monte Carlo Exploration-Exploitation Trade-Off for Buffer Sampling
Julius Ott, Lorenzo Servadei, Jose A. Arjona-Medina, Enrico Rinaldi, Gianfranco Mauro, Daniela Sanchez Lopera +4
ICASSP 2023accepted
Data selection is essential for any data-based optimization technique, such as Reinforcement Learning. State-of-the-art sampling strategies for the experience replay buffer improve the performance of the Reinforcement Learning agent. However, they do not incorporate uncertainty in the Q-Value estima…