Efficient Offline Meta-Reinforcement Learning via Robust Task Representations and Adaptive Policy Generation

Abstract

Argumentation is a central subarea of Artificial Intelligence (AI) for modeling and reasoning about arguments. The semantics of abstract argumentation frameworks (AFs) is given by sets of arguments (extensions) and conditions on the relationship between arguments, such as stable or admissible. Today's solvers implement tasks such as finding extensions, deciding credulously or skeptically acceptance, counting, or enumerating extensions. While these tasks are well charted, the area between decision and counting/enumeration and fine-grained reasoning requires expensive reasoning so far. We introduce a novel concept (facets) for reasoning between decision and enumeration. Facets are arguments that belong to some extensions (credulous) but not to all extensions (skeptical). They are most natural when a user aims to navigate, filter, or comprehend specific arguments, according to their needs. We study the complexity and show that tasks involving facets are much easier than counting extensions. Finally, we provide an implementation, and conduct experiments to demonstrate feasibility.