Publications

Yi Zhao, Aidan Scannell, Wenshuai Zhao, Cui Yuxin, Tianyu Cui, Le Chen, Arno Solin, Juho Kannala, Joni Pajarinen (2025). Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data. arXiv preprint arXiv:2502.19544v2.

Yi Zhao, Aidan Scannell, Cui Yuxin, Tianyu Cui, Le Chen, Arno Solin, Juho Kannala, Joni Pajarinen (2025). Generalist World Model Pre-Training for Efficient Reinforcement Learning. ICLR 2025 Workshop on World Models: Understanding, Modelling and Scaling.

Aidan Scannell, Mohammadreza Nakhaei, Kalle Kujanpää, Yi Zhao, Kevin Luck, Arno Solin, Joni Pajarinen (2025). Discrete Codebook World Models for Continuous Control. In The Thirteenth International Conference on Learning Representations (ICLR).

Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen (2025). Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning. In AAAI 2025".

Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen (2024). iQRL - Implicitly Quantized Representations for Sample-efficient Reinforcement Learning. arXiv preprint arXiv:2406.02696.

Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen (2024). Quantized Representations Prevent Dimensional Collapse in Self-predictive RL. ICML Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET).

Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen (2024). Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning. In 4th Annual Conference on Learning for Dynamics and Control (L4DC).

Aidan Scannell

Equal contribution

, Riccardo Mereu

Equal contribution

, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin (2024). Function-space Parameterization of Neural Networks for Sequential Learning. In The Twelth International Conference on Learning Representations (ICLR).

Aidan Scannell

Equal contribution

, Riccardo Mereu

Equal contribution

, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin (2023). Sparse Function-space Representation of Neural Networks. In ICML 2023 Workshop on Duality Principles for Modern Machine Learning.

Aidan Scannell, Carl Henrik Ek, Arthur Richards (2023). Mode-constrained Model-based Reinforcement Learning via Gaussian Processes. In 26th International Conference on Artificial Intelligence and Statistics (AISTATS).