Responsibility in Extensive Form Games

TL;DR

This paper introduces a new definition of seeing-to-it responsibility in multi-agent sequential settings, explores the relationship with counterfactual responsibility, and examines the responsibility gap.

Contribution

It proposes an amalgamated seeing-to-it responsibility definition for sequential multi-agent scenarios and analyzes the non-definability and responsibility gap between responsibility types.

Findings

New seeing-to-it responsibility definition proposed

Responsibility gap exists between responsibility types

Higher-order responsibility can bridge the gap

Abstract

Two different forms of responsibility, counterfactual and seeing-to-it, have been extensively discussed in the philosophy and AI in the context of a single agent or multiple agents acting simultaneously. Although the generalisation of counterfactual responsibility to a setting where multiple agents act in some order is relatively straightforward, the same cannot be said about seeing-to-it responsibility. Two versions of seeing-to-it modality applicable to such settings have been proposed in the literature. Neither of them perfectly captures the intuition of responsibility. This paper proposes a definition of seeing-to-it responsibility for such settings that amalgamate the two modalities. This paper shows that the newly proposed notion of responsibility and counterfactual responsibility are not definable through each other and studies the responsibility gap for these two forms of responsibility. It shows that although these two forms of responsibility are not enough to ascribe responsibility in each possible situation, this gap does not exist if higher-order responsibility is taken into account.