538 citations
- University College LondonGB83 papers
- University of CambridgeGB12 papers
- University of OxfordGB12 papers
- Institut national de recherche en sciences et technologies du numériqueFR8 papers
- Max Planck Institute for Intelligent SystemsDE7 papers
- University of LondonGB7 papers
- Gatsby Charitable FoundationGB6 papers
- The Institute of Statistical MathematicsJP6 papers
- University of BristolGB6 papers
- Google DeepMind (United Kingdom)GB4 papers
- Princeton UniversityUS4 papers
- University of California, BerkeleyUS4 papers
5 papers · 2 filters
Towards an Understanding of Default Policies in Multitask Policy Optimization
Ted Moskovitz, Michael Arbel, Jack Parker-Holder +1
Much of the recent success of deep reinforcement learning has been driven by regularized policy optimization (RPO) algorithms with strong performance across multiple domains. In th…
An Analytical Theory of Curriculum Learning in Teacher-Student Networks
Luca Saglietti, Stefano Sarao Mannelli, Andrew Saxe
In humans and animals, curriculum learning -- presenting data in a curated order - is critical to rapid learning and effective pedagogy. Yet in machine learning, curricula are not…
Probing transfer learning with a model of synthetic correlated datasets
Federica Gerace, Luca Saglietti, Stefano Sarao Mannelli +2
Transfer learning can significantly improve the sample efficiency of neural networks, by exploiting the relatedness between a data-scarce target task and a data-abundant source tas…
Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction
Afsaneh Mastouri, Yuchen Zhu, Limor Gultchin +5
We address the problem of causal effect estimation in the presence of unobserved confounding, but where proxies for the latent confounder(s) are observed. We propose two kernel-bas…
Tactical Optimism and Pessimism for Deep Reinforcement Learning
Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano +2
In recent years, deep off-policy actor-critic algorithms have become a dominant approach to reinforcement learning for continuous control. One of the primary drivers of this improv…