Accepted Papers:
Accepted Papers:
- Christos Kaplanis, Murray Shanahan and Claudia Clopath. Continual Reinforcement Learning with Complex Synapses.
- Vitchyr Pong, Ashvin Nair, Murtaza Dalal, Shikhar Bahl, Steven Lin and Sergey Levine. Visual Goal-Conditioned Reinforcement Learning by Representational Learning.
- Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn and Sergey Levine. Unsupervised Meta-Learning for Reinforcement Learning.
- Sebastian Farquhar and Yarin Gal. Towards Robust Evaluations of Continual Learning.
- Jiayu Yao, Taylor Kilian, Finale Doshi-Velez and George Konidaris. Direct Policy Transfer via Hidden Parameter Markov Decision Processes.
- Craig Sherstan, Marlos C. Machado and Patrick M. Pilarski. Incrementally Added GVFs are Learned Faster with the Successor Representation.
- Lucas Lehnert and Michael L. Littman. Transfer with Model Features in Reinforcement Learning.
- Benjamin van Niekerk, Steven James, Adam Earle and Benjamin Rosman. Will it Blend? Composing Value Functions in Reinforcement Learning.
- Giulia Denevi, Carlo Ciliberto, Dimitris Stamos and Massimiliano Pontil. Online Meta-Learning with Generalization Guarantees.
- Pratik Gajane, Ronald Ortner and Peter Auer. A Sliding-Window Approach for Reinforcement Learning in MDPs with Arbitrarily Changing Rewards and Transitions.
- Keren-Or Berkers, Jonathan Giron and Friedman Doron. Algorithmic Induction of Physiological State: First Steps.
- Shagun Sodhani and Sarath Chandar. On Capacity Expansion in Recurrent Neural Networks for Lifelong Learning.
- 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.
- Khimya Khetarpal and Doina Precup. Attend Before you Act: Leveraging human visual attention for continual learning.
- 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.
- Sungryull Sohn, Junhyuk Oh and Honglak Lee. Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies.