938 citations
- Turing InstituteGB120 papers
- University of CambridgeGB50 papers
- Queen Mary University of LondonGB44 papers
- University College LondonGB42 papers
- University of OxfordGB38 papers
- Imperial College LondonGB32 papers
- University of WarwickGB32 papers
- University of ManchesterGB26 papers
- University of EdinburghGB18 papers
- University of ExeterGB17 papers
- Institut national de recherche en sciences et technologies du numériqueFR15 papers
- Centre National de la Recherche ScientifiqueFR11 papers
4 papers · 2 filters
Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values
Mahed Abroshan, Kai Hou Yip, Cem Tekin +1
In high-stakes applications of data-driven decision making like healthcare, it is of paramount importance to learn a policy that maximizes the reward while avoiding potentially dan…
Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski +2
Approximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has many applications acr…
Lifetime policy reuse and the importance of task capacity
David M. Bossens, Adam J. Sobey
A long-standing challenge in artificial intelligence is lifelong reinforcement learning, where learners are given many tasks in sequence and must transfer knowledge between tasks w…
SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
Chi Ian Tang, Ignacio Perez-Pozuelo, Dimitris Spathis +3
Machine learning and deep learning have shown great promise in mobile sensing applications, including Human Activity Recognition. However, the performance of such models in real-wo…