Author:Hal Ashton

Publications
Defining and Identifying the Legal Culpability of Side Effects Using Causal Graphs Hal Ashton EasyChair Preprint 7303
The Problem of Behaviour and Preference Manipulation in AI Systems Hal Ashton and Matija Franklin EasyChair Preprint 7281
What criminal and civil law tells us about Safe RL techniques to generate law-abiding behaviour Hal Ashton EasyChair Preprint 4844
Definitions of Intent for AI Derived From Common Law Hal Ashton EasyChair Preprint 4422

Keyphrases

AI, Artificial Intelligence², auto induced distributional shift, autonomous agents², behaviour change, causal DAG, causal model, causal reasoning, choice architecture, cooperative inverse reinforcement learning, Culpability, human preference, Intent³, Inverse Reinforcement Learning, Law and AI, legal reasoning, Libertarian Paternalism, manipulation, mens rea, preferences, Reinforcement Learning, Safe Reinforcement Learning, safe rl research, safety, Safety Robustness and Trustworthiness, side effect, structural causal influence model, Structural Causal Model², value alignment.