Publications

Peer-Reviewed Conferences

Successor-Predecessor Intrinsic Exploration.
Changmin Yu, Neil Burgess, Maneesh Sahani, Samuel J. Gershman.
Advances in Neural Information Processing Systems, 37 (2023).

Unsupervised Representation Learning with Recognition-Parametrised Probabilistic Models.
William Walker, Hugo Soulat, Changmin Yu, Maneesh Sahani.
International Conference on Artificial Intelligence and Statistics, vol. 206 of Proceedings of Machine Learning Research (2023).

Structured Recognition for Generative Models with Explaining Away.
Changmin Yu, Hugo Soulat, Neil Burgess, Maneesh Sahani.
Advances in Neural Information Processing Systems, 36 (2022).

Learning State Representations via Retracing in Reinforcement Learning.
Changmin Yu, Dong Li, Jianye Hao, Jun Wang, and Neil Burgess.
Tenth International Conference on Learning Representations (2021).

What About Inputting Policy in Value Function: Policy Representation and Policy-Extended Value Function Approximator.
Hongyao Tang, Zhaopeng Meng, Jianye Hao, Chen Chen, Daniel Graves, Dong Li, Changmin Yu, Hangyu Mao, Wulong Liu, Yaodong Yang, Wenyuan Tao, Li Wang.
In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 36, No. 8, pp. 8441-8449). (2020).

Prediction and Generalisation over Directed Actions by Grid Cells.
Changmin Yu, Timothy E.J. Behrens, Neil Burgess.
Ninth International Conference on Learning Representations (2020).

Peer-Reviewed Journals

Deep Kernel Learning Approach to Engine Emissions Modeling.
Changmin Yu, Marko Seslija, George Brownbridge, Sebastian Mosbach, Markus Kraft, Mohammad Parsi, Mark Davis,Vivian Page, and Amit Bhave.
In Data-Centric Engineering 1 (2020).

Conference Workshops

Leveraging Episodic Memory to Improve World Models for Reinforcement Learning.
Julian Coda-Forno, Changmin Yu, Qinghai Guo, Zafeirios Fountas, Neil Burgess. Memory in Artificial and Real Intelligence workshop at NeurIPS 2022.

Learning State Representations via Temporal Cycle-Consistency Constraint in Model-Based Reinforcement Learning.
Changmin Yu, Dong Li, Hangyu Mao, Jianye Hao, Neil Burgess.
Self-Supervision for Reinforcement Learning Workshop at ICLR 2021.

Preprints

SEREN: Knowing When to Explore and When to Exploit.
Changmin Yu, David Mguni, Dong Li, Aivar Sootla, Jun Wang, Neil Burgess.
arXiv preprint arXiv:2205.15064 (2022).

DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention.
David Henry Mguni, Usman Islam, Yaqi Sun, Xiuling Zhang, Joel Jennings, Aivar Sootla, Changmin Yu, Jun Wang, and Yaodong Yang.
arXiv preprint arXiv:2110.14468 (2021).