Towards a general blueprint for continual reinforcement learning - Doina Precup - CoLLAs 2024
Автор: Conference on Lifelong Learning Agents (CoLLAs)
Загружено: 2024-10-15
Просмотров: 459
Abstract: Intelligent agents must be able to learn by interacting with their environment and to adapt to changes. Continual reinforcement learning provides a natural way to model this process. In this talk, I will discuss my point of view regarding the way in which we shouldformalize continual reinforcement learning, and the types of methods can be used to tackle it. In particular, I will discuss the role of representations that allow an agent to generalize its knowledge quickly to new circumstances.
Bio: Doina Precup splits her time between McGill University / Mila, where she holds a Canada-CIFAR AI chair, and Google DeepMind, where she is a Research Director. Her research interests are in the areas of reinforcement learning, reasoning under uncertainty, time series analysis, and diverse applications of machine learning in areas that have a social impact, such as health care. In 2022, she was elected Fellow of the Royal Society of Canada in recognition of her work in these fields. She is also a senior fellow of CIFAR’s Learning in Machines and Brains program.
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
