Accepted Papers:


  1. Christos Kaplanis, Murray Shanahan and Claudia Clopath. Continual Reinforcement Learning with Complex Synapses.
  2. Vitchyr Pong, Ashvin Nair, Murtaza Dalal, Shikhar Bahl, Steven Lin and Sergey Levine. Visual Goal-Conditioned Reinforcement Learning by Representational Learning.
  3. Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn and Sergey Levine. Unsupervised Meta-Learning for Reinforcement Learning.
  4. Sebastian Farquhar and Yarin Gal. Towards Robust Evaluations of Continual Learning.
  5. Jiayu Yao, Taylor Kilian, Finale Doshi-Velez and George Konidaris. Direct Policy Transfer via Hidden Parameter Markov Decision Processes.
  6. Craig Sherstan, Marlos C. Machado and Patrick M. Pilarski. Incrementally Added GVFs are Learned Faster with the Successor Representation.
  7. Lucas Lehnert and Michael L. Littman. Transfer with Model Features in Reinforcement Learning.
  8. Benjamin van Niekerk, Steven James, Adam Earle and Benjamin Rosman. Will it Blend? Composing Value Functions in Reinforcement Learning.
  9. Giulia Denevi, Carlo Ciliberto, Dimitris Stamos and Massimiliano Pontil. Online Meta-Learning with Generalization Guarantees.
  10. Pratik Gajane, Ronald Ortner and Peter Auer. A Sliding-Window Approach for Reinforcement Learning in MDPs with Arbitrarily Changing Rewards and Transitions.
  11. Keren-Or Berkers, Jonathan Giron and Friedman Doron. Algorithmic Induction of Physiological State: First Steps.
  12. Shagun Sodhani and Sarath Chandar. On Capacity Expansion in Recurrent Neural Networks for Lifelong Learning.
  13. Shayegan Omidshafiei, Dong-Ki Kim, Miao Liu, Gerald Tesauro, Matthew Riemer, Christopher Amato, Murray Campbell and Jonathan How. Learning to Teach in Cooperative Multiagent Reinforcement Learning.
  14. Khimya Khetarpal and Doina Precup. Attend Before you Act: Leveraging human visual attention for continual learning.
  15. Danijar Hafner, Ian Fischer, Timothy Lillicrap, David Ha, James Davidson and Honglak Lee. Learning Unsupervised Latent Dynamics Models for Multi-task Continuous Control from Pixels.
  16. Sungryull Sohn, Junhyuk Oh and Honglak Lee. Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies.