Sökning: "Tomas Landelius"
Hittade 2 avhandlingar innehållade orden Tomas Landelius.
1. Behavior Representation by Growing a Learning Tree
Sammanfattning : The work presented in this thesis is based on the basic idea of learning by reinforcement, within the theory of behaviorism. The reason for this choice is the generality of such an approach, especially that the reinforcement learning paradigm allows systems to be designed which can improve their behavior beyond that of their teacher. LÄS MER
2. Reinforcement Learning and Distributed Local Model Synthesis
Sammanfattning : Reinforcement learning is a general and powerful way to formulate complex learning problems and acquire good system behaviour. The goal of a reinforcement learning system is to maximize a long term sum of instantaneous rewards provided by a teacher. LÄS MER