Search Results for author:
Found 4 papers, 0 papers with code
The Reasons that Agents Act: Intention and Instrumental Goals
In addition, we show how our definition relates to past concepts, including actual causality, and the notion of instrumental goals, which is a core idea in the literature on safe AI agents.
Honesty Is the Best Policy: Defining and Mitigating AI Deception
There are a number of existing definitions of deception in the literature on game theory and symbolic AI, but there is no overarching theory of deception for learning agents in games.
Experiments with Detecting and Mitigating AI Deception
How to detect and mitigate deceptive AI systems is an open problem for the field of safe and trustworthy AI.
Argumentative Reward Learning: Reasoning About Human Preferences
We define a novel neuro-symbolic framework, argumentative reward learning, which combines preference-based argumentation with existing approaches to reinforcement learning from human feedback.
