3

iQRL – Implicitly Quantized Representations for Sample-efficient Reinforcement Learning

Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen

Quantized Representations Prevent Dimensional Collapse in Self-predictive RL

Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen

Sparse Function-space Representation of Neural Networks

Aidan Scannell, Riccardo Mereu, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin