Publications

Journal

Influence-aware memory architectures for deep reinforcement learning in POMDPs.
Miguel Suau, Jinke He, Elena Congeduti, Rolf A.N. Starre, Aleksander Czechowski, Frans A. Oliehoek.
Neural Computing and Applications, 2022.

Conference

Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems.
Miguel Suau, Jinke He, Matthijs TJ Spaan, Frans A Oliehoek.
International Conference on Machine Learning (ICML), 2022.

Online Planning in POMDPs with Self-Improving Simulator.
Jinke He, Miguel Suau, Hendrik Baier, Michael Kaisers, and Frans A. Oliehoek.
International Joint Conference on Artificial Intelligence (IJCAI), 2022.

Influence-Augmented Online Planning for Complex Environments.
Jinke He, Miguel Suau, Frans Oliehoek.
Conference on Neural Information Processing Systems (NeurIPS), 2020.

Multitask Soft Option Learning.
Maximilian Igl, Andrew Gambardella, Jinke He, Nantas Nardelli, N. Siddharth, Wendelin Boehmer, Shimon Whiteson.
Conference on Uncertainty in Artificial Intelligence (UAI), 2020.

Workshop

Robust Ensemble Adversarial Model-Based Reinforcement Learning.
Daniele Foffano, Jinke He and Frans A. Oliehoek.
Adaptive and Learning Agents Workshop (ALA) at AAMAS, 2022.

Soft Option Transfer.
Jinke He, Maximilian Igl, Matthew Smith, Wendelin Boehmer, Shimon Whiteson.
Learning Transferable Skills Workshop at NeurIPS, 2019.