Implicitly Quantized Representations for Reinforcement Learning
24 Mar, 2024·,,,,,·
1 min read
Aidan Scannell
Kalle Kujanpää
Yi Zhao
Mohammadreza Nakhaei
Arno Solin
Joni Pajarinen

Learning representations for reinforcement learning (RL) has shown much promise for continuous control. In this project, we investigate using vector quantization to prevent representation collapse when learning representations for RL using a self-supervised latent-state consistency loss.