When is a Prediction Knowledge?
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 proposals, the underlying assumptions of such claims have consequences for the systems we design. These consequences manifest in both the way we choose to structure predictive knowledge architectures, and how we evaluate them. In this paper, we take a first step to formalizing predictive knowledge by discussing the relationship of predictive knowledge learning methods to existing theories of knowledge in epistemology. Specifically, we explore the relationships between Generalized Value Functions and epistemic notions of Justification and Truth.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingPredictionreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Interactive Elicitation of Knowledge on Feature Relevance Improves Predictions in Small Data Sets
Providing accurate predictions is challenging for machine learning algorithms when the number of features is larger than the number of samples in the data. Prior knowledge can improve machine learning models by indicatin…
BIG-bench Machine LearningPredictionSmall Data Image ClassificationDistilling Knowledge From a Deep Pose Regressor Network
This paper presents a novel method to distill knowledge from a deep pose regressor network for efficient Visual Odometry (VO). Standard distillation relies on "dark knowledge" for successful knowledge transfer. As this k…
PredictionregressionTransfer LearningVisual OdometryTrustworthy Prediction with Gaussian Process Knowledge Scores
Probabilistic models are often used to make predictions in regions of the data space where no observations are available, but it is not always clear whether such predictions are well-informed by previously seen data. In …
Anomaly DetectionGPRImputationPredictionCan Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs
Large Language Models (LLMs) are widely used for temporal prediction, but their reliance on pretraining data raises contamination concerns, as accurate predictions on pre-cutoff test data may reflect memorization rather …
3D Scene Graph Prediction on Point Clouds Using Knowledge Graphs
3D scene graph prediction is a task that aims to concurrently predict object classes and their relationships within a 3D environment. As these environments are primarily designed by and for humans, incorporating commonse…
Graph GenerationKnowledge GraphsPredictionScene Graph Generation