Lifelong Learning: A Reinforcement Learning Approach
Workshop at The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM)
Wednesday, July 10, 2019 , 1:00PM - McGill University, Montréal, Québec, Canada
One of the most significant and challenging open problem in Artificial Intelligence (AI) is the problem of Lifelong Learning. Lifelong Machine Learning considers systems that can continually learn many tasks (from one or more domains) over a lifetime.
A lifelong learning system efficiently and effectively
- retains the knowledge it has learned from different tasks;
- selectively transfers knowledge (from previously learned tasks) to facilitate learning of new tasks; and
- ensures the effective and efficient interaction between (1) and (2).
Lifelong learning techniques are applicable to almost all machine learning paradigms and very relevant for training intelligent autonomous agents that would need to operate and make decisions over extended periods of time. Despite the hype surrounding lifelong learning (and related areas like transfer and multi-task learning), lifelong learning is still in its infancy. Many issues currently exist such as learning general representations, catastrophic forgetting, efficient knowledge retention mechanisms and hierarchical abstractions. Much work has been done in the Reinforcement Learning (RL) community to tackle different elements of lifelong learning. Active research topics include hierarchical abstractions, transfer learning, multi-task learning and curriculum learning. With the emergence of powerful function approximators such as in Deep Learning, we feel that now is a perfect time to provide a forum to discuss ways to move forward and provide a truly general lifelong learning framework, using RL-based algorithms, with much more rigour than ever before.
This workshop is a step in that direction. The aim is the bring together experts and practitioners from different communities - working on the different elements of lifelong learning - to try and find a synergy between the various techniques. Both deep and non-deep reinforcement learning works would be welcome.