When Is A Prediction Knowledge?

Abstract

Within Reinforcement Learning, there is a growing collection of research which aims to express all of an agent's knowledge of the world through predictions about sensation, behaviour, and time. This work can be seen not only as a collection of architectural proposals, but also as the beginnings of a theory of machine knowledge in reinforcement learning. Recent work has expanded what can be expressed using predictions, and developed applications which use predictions to inform decision-making on a variety of synthetic and real-world problems. While promising, we here suggest that the notion of predictions as knowledge in reinforcement learning is as yet underdeveloped: some work explicitly refers to predictions as knowledge, what the requirements are for considering a prediction to be knowledge have yet to be well explored. This specification of the necessary and sufficient conditions of knowledge is important; even if claims about the nature of knowledge are left implicit in technical

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykearney2019when

Related papers

• Predictive Representations: Building Blocks Of Intelligence (2024)8.09
• Foundations For Transfer In Reinforcement Learning: A Taxonomy Of Knowledge Modalities (2023)0.00
• Reinforcement Learning With Knowledge Representation And Reasoning: A Brief Survey (2023)0.00
• Predicting Future Actions Of Reinforcement Learning Agents (2024)3.58
• Finding Useful Predictions By Meta-gradient Descent To Improve Decision-making (2021)0.00
• What Should I Know? Using Meta-gradient Descent For Predictive Feature Discovery In A Single Stream Of Experience (2022)0.00
• Embedded Universal Predictive Intelligence: A Coherent Framework For Multi-agent Learning (2025)0.00
• Predictive Information Accelerates Learning In RL (2020)0.00