3

Generalist World Model Pre-Training for Efficient Reinforcement Learning

Sample-efficient robot learning is a longstanding goal in robotics. Inspired by the success of scaling in vision and language, the …

Yi Zhao, Aidan Scannell, Cui Yuxin, Tianyu Cui, Le Chen, Arno Solin, Juho Kannala, Joni Pajarinen

iQRL - Implicitly Quantized Representations for Sample-efficient Reinforcement Learning

Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient …

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

iQRL - Implicitly Quantized Representations for Sample-efficient Reinforcement Learning

Quantized Representations Prevent Dimensional Collapse in Self-predictive RL

Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient …

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

Sparse Function-space Representation of Neural Networks

Deep neural networks (NNs) are known to lack uncertainty estimates and struggle to incorporate new data. We present a method that …

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

Sparse Function-space Representation of Neural Networks

Identifiable Mixtures of Sparse Variational Gaussian Process Experts

Mixture models are inherently unidentifiable as different combinations of component distributions and mixture weights can generate the …

Aidan Scannell, Carl Henrik Ek, Arthur Richards