KNOWLEDGE TRANSFER AND LEARNING: PROBLEMS OF KNOWLEDGE TRANSFER ASSOCIATED WITH TRYING TO SHORT-CIRCUIT THE LEARNING CYCLE

Knowledge Transfer and Learning: Problems of Knowledge Transfer Associated with Trying to Short-circuit the Learning Cycle

conceptualization COGNITIVE WORK BEHAVIOURAL WORK Figure 1: The Learning Cycle and The Cognitive and Behavioural Work involved in Learning The learning cycle emphasizes that there is both behavioural and cognitive work involved in learning (Huber, 1991). So we can learn from our actual experiences (concrete experience) and experiment and practice to find out what works best (active experimentat...

Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents

This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...

Knowledge Transfer in Reinforcement Learning

Knowledge Transfer in Artificial Learning

This document presents the main research problems addressed during my PhD studies. All these researches are led inside the two teams DBWeb in Télécom ParisTech and LInK (Learning and Integration of Knowledge) in AgroParisTech, both located in Paris, and supervised by Pr. Jean-Louis Dessalles and Pr. Antoine Cornuéjols. My researches focus on learning theory both in the perspective of symbolic m...

Learning to Transfer Knowledge between Reference Systems

Representation and inference of spatial knowledge play a fundamental role in spatial reasoning, which itself is an important component of many applications such as Geographic Information Systems or robotics. This paper discusses how an existing relation between speakerrelative and absolute spatial reference systems can be automatically learned by an inductive relational machine learning system.