Representations in zero-shot meta-reinforcement learning

Thesis

A long-standing goal in the field of Artificial Intelligence (AI) is to create autonomous agents capable of making a sequence of decisions to interact with the world. When interacting with its environment, an agent will encounter new situations that it has not previously encountered and for which we cannot provide an explicit representation of the environment. In this case, the agent must learn about its environment through interaction allowing trial and error -- a problem well modeled by ...

Expand abstract

Authors: Beck, J

• DOI: 10.5287/ora-gwyn1maaj
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: sequence models; reinforcement learning; agent; in-context learning; meta-reinforcement learning; meta-RL; zero-shot; few-shot; memory; learning to learn
• Subjects: Machine learning; Artificial intelligence; Meta-Reinforcement learning; Reinforcement learning