Enforcing ethical goals over reinforcement-learning policies

Abstract

Abstract Recent years have yielded many discussions on how to endow autonomous agents with the ability to make ethical decisions, and the need for explicit ethical reasoning and transparency is a persistent theme in this literature. We present a modular and transparent approach to equip autonomous agents with the ability to comply with ethical prescriptions, while still enacting pre-learned optimal behaviour. Our approach relies on a normative supervisor module, that integrates a theorem prover for defeasible deontic logic within the control loop of a reinforcement learning agent. The supervisor operates as both an event recorder and an on-the-fly compliance checker w.r.t. an external norm base. We successfully evaluated our approach with several tests using variations of the game Pac-Man, subject to a variety of “ethical” constraints.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 19 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.