10.1k citations
- Google (United States)US161 papers
- Google (United Kingdom)GB73 papers
- University of OxfordGB33 papers
- Massachusetts Institute of TechnologyUS25 papers
- University College LondonGB25 papers
- University of AlbertaCA19 papers
- Imperial College LondonGB18 papers
- University of CambridgeGB16 papers
- McGill UniversityCA15 papers
- Stanford UniversityUS15 papers
- University of TorontoCA15 papers
- University of California, BerkeleyUS14 papers
6 papers · 2 filters
Deep Reinforcement Learning and the Deadly Triad
Hado van Hasselt, Yotam Doron, Florian Strub +3
We know from reinforcement learning theory that temporal difference learning can fail in certain cases. Sutton and Barto (2018) identify a deadly triad of function approximation, b…
Attend Before you Act: Leveraging human visual attention for continual learning
Khimya Khetarpal, Doina Precup
When humans perform a task, such as playing a game, they selectively pay attention to certain parts of the visual input, gathering relevant information and sequentially combining i…
Organizing Experience: A Deeper Look at Replay Mechanisms for Sample-based Planning in Continuous State Domains
Yangchen Pan, Muhammad Zaheer, Adam White +2
Model-based strategies for control are critical to obtain sample efficient learning. Dyna is a planning paradigm that naturally interleaves learning and planning, by simulating one…
Learning Awareness Models
Brandon Amos, Laurent Dinh, Serkan Cabi +7
We consider the setting of an agent with a fixed body interacting with an unknown and uncertain external world. We show that models trained to predict proprioceptive information ab…
Continual Reinforcement Learning with Complex Synapses
Christos Kaplanis, Murray Shanahan, Claudia Clopath
Unlike humans, who are capable of continual learning over their lifetimes, artificial neural networks have long been known to suffer from a phenomenon known as catastrophic forgett…
Learning to Search with MCTSnets
Arthur Guez, Théophane Weber, Ioannis Antonoglou +5
Planning problems are among the most important and well-studied problems in artificial intelligence. They are most typically solved by tree search algorithms that simulate ahead in…