Cong Lu

Cong Lu

DPhil Student

University of Oxford

Biography

I am a DPhil student supervised by Prof. Michael A. Osborne and Prof. Yee Whye Teh. I am a member of the MLRG and OxCSML groups. My research interests span deep reinforcement learning, meta-learning and Bayesian Optimisation. I am particularly interested in offline reinforcement learning (including generalisation to unseen tasks and uncertainty quantification for pessimistic MDPs) and reinforcement learning as probabilistic inference. I obtained my undergraduate degree in Mathematics and Computer Science from the University of Oxford.

Interests
  • Deep Reinforcement Learning
  • Meta-Learning
  • Bayesian Optimisation
Education
  • MMathCompSci in Mathematics and Computer Science, 2019

    University of Oxford

Recent Publications

(2021). Augmented World Models Facilitate Zero-Shot Dynamics Generalization From A Single Offline Environment. In 38th International Conference on Machine Learning, 2021.

Cite arXiv Website PDF

(2021). Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning. In 38th International Conference on Machine Learning, 2021.

Cite arXiv PDF

(2021). On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations. In 34th Advances in Neural Information Processing Systems, 2021.

Cite Website PDF

(2021). Revisiting Design Choices in Offline Model Based Reinforcement Learning. In ICML Reinforcement Learning for Real Life Workshop, 2021.

Cite PDF

(2021). Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces. In 38th International Conference on Machine Learning, 2021.

Cite arXiv PDF

(2021). VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning. In Journal of Machine Learning Research (to appear), 2021.

Cite