One of the most significant and challenging open problems 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:
1. retains the knowledge it has learned from different tasks;
2. selectively transfers knowledge (from previously learned tasks) to facilitate the learning of new tasks;
3. ensures the effective and efficient interaction between (1) and (2).
Lifelong Learning introduces several fundamental challenges in training models that generally do not arise in a single task batch learning setting. This includes problems like catastrophic forgetting and capacity saturation. This workshop aims to explore solutions for these problems in both supervised learning and reinforcement learning settings.
| Opening Comments (Introduction) | |
| Challenges & Opportunities in Lifelong Reinforcement Learning by Katja Hoffman (Talk) | |
| Q&A with Katja Hoffman (Q&A) | |
| Never-ending Learning by Partha Pratim Talukdar (Talk) | |
| Q&A with Partha Pratim Talukdar (Q&A) | |
| Contributed Talk: Continual Deep Learning by Functional Regularisation of Memorable Past (Talk) | |
| Virtual Poster Session #1 (Poster Session) | |
| Credit assignment and meta-learning in a single lifelong trial by Jürgen Schmidhuber (Talk) | |
| Q&A with Jürgen Schmidhuber (Q&A) | |
| Contributed Talk: Combining Variational Continual Learning with FiLM Layers (Talk) | |
| Contributed Talk: Wandering Within a World: Online Contextualized Few-Shot Learning (Talk) | |
| Invited Talk: Lifelong Learning: Towards Broad and Robust AI by Irina Rish (Talk) | |
| Q&A with Irina Rish (Q&A) | |
| Virtual Poster Session #2 (Poster Session) | |
| Contributed Talk: Deep Reinforcement Learning amidst Lifelong Non-Stationarity (Talk) | |
| Contributed Talk: Lifelong Learning of Factored Policies via Policy Gradients (Talk) | |
| The FOAK Cycle for Model-based Life-long Learning by Rich Sutton (Talk) | |
| Q&A by Rich Sutton (Q&A) | |
| Contributed Talk: Gradient Based Memory Editing for Task-Free Continual Learning (Talk) | |
| Panel Discussion (Discussion Panel) | |
| Concluding Remarks | |
| Accepted Papers (Demonstration) | |