Matthew Riemer
Papers
2
Total Citations
207
H-Index
2
About
Matthew Riemer is a leading voice in the quest to build artificial intelligence that can learn continuously, just like humans. His primary research focuses on continual reinforcement learning (RL), lifelong learning, and non-stationary environments—areas critical for developing AI that adapts without forgetting. Riemer’s major contribution is his seminal review, *"Towards Continual Reinforcement Learning: A Review and Perspectives,"* which has garnered over 200 combined citations. This work systematically maps the fragmented landscape of continual RL, offering a unified taxonomy of formulations and approaches while arguing persuasively that RL is the natural framework for studying lifelong learning. By clarifying key challenges—such as catastrophic forgetting and stability-plasticity trade-offs—Riemer has provided a foundational roadmap for researchers. His impact extends beyond the review; his insights are shaping how the field designs agents that can accumulate knowledge over time. For students and researchers, Riemer’s work is an essential starting point for understanding how to build AI that truly learns a lifetime.
Research Focus
Key Achievements
Top Papers
- 1Towards Continual Reinforcement Learning: A Review and Perspectives179 citations · 2022
- 2Towards Continual Reinforcement Learning: A Review and Perspectives28 citations · 2020