Polani, Daniel - School of Computer Science, University of Hertfordshire

• Behavior Classi cation with Self-Organizing Maps
• Backtrack Control Consider: the following pseudo-Pascal code
• Bold Hearts 2003: Skill Learning Via InformationTheoretical
• Towards a Probabilistic Asynchronous Linear Control Theory
• Bold Hearts 2003: Skill Learning Via Information-Theoretical
• On Individuality, Emergence and Information Preservation
• Artificial Intelligence Daniel Polani
• Advanced Symbolic Arti cial Intelligence
• Order Parameters for SelfOrganizing Maps
• Preventing Bluff Agent Invasions in Honest Societies Robert Lowe and Daniel Polani
• Eugenic Neuro-Evolution for Reinforcement Learning Daniel Polani
• Investigations of the Dynamics of an Evolving Agent Population Thomas Uthmann and Daniel Polani
• Category AL On the development of spectral properties
• Artificial Intelligence What is AI?
• Introduction into Unix/Linux Introduction into Computing Environments
• University of Hertfordshire Dept. of Computer Science
• Introduction into Python Python 3: Further Lists and Other Data Structures
• Using Real-Time Recognition of Human-Robot Interaction Styles for Creating Adaptive Robot Behaviour in Robot-Assisted Play
• Exploring Empowerment as a Basis for Quantifying Sustainability Jan T. Kim and Daniel Polani
• A Method for Incorporation of New Evidence to Improve World State Estimation
• The Effects on Visual Information in a Robot in Environments with Oriented Contours
• Family Example parent(tom, bob).
• Optimizing Potential Information Transfer with Self-referential Memory
• University of Hertfordshire Dept. of Computer Science
• University of Hertfordshire Dept. of Computer Science
• Propositional and Predicate Logic A Sightseeing Overview
• Criticbased Learning of Actions with SelfOrganising Feature Maps
• Constructive Artificial Intelligence Introduction
• From Unknown Sensors and Actuators to Visually Guided Lars Olsson, Chrystopher L. Nehaniv, Daniel Polani
• Artificial Intelligence Daniel Polani
• Introduction into Python Daniel Polani
• Expert Systems See [Bratko 1990]
• Distributed Systems Multiagent Systems
• Introduction into Python Python 1: Examples, Variables, Scalars and Lists
• Homeokinesis A new principle to back up evolution with learning
• Organization Measures for SelfOrganizing Maps Daniel Polani
• Sensory Channel Grouping and Structure from Uninterpreted Sensor Data Lars Olsson, Chrystopher L. Nehaniv, and Daniel Polani
• Evolution of the spectral properties of a visual agent receptor Achim Liese Daniel Polani
• \Dangerous and beautiful" in Prolog: \necessary"
• Tracking Information Flow through the Environment: Simple Cases of Stigmergy
• Sequential Learning with LS-SVM for Large-Scale Data Sets
• Depth-First Search: finds solution path Sol from given node N to some goal node (there can be
• University of Hertfordshire Dept. of Computer Science
• First steps in Prolog To read in a le
• Constructive Artificial Intelligence Daniel Polani
• Grunde fur diese Art der Datenubertragung: weniger Fehleranfallig
• Learning RoboCup-Keepaway with Kernels Tobias Jung
• Artificial Intelligence Markovian Decision Processes
• Introduction into Python Python 4: Advanced Features
• Least Squares SVM for Least Squares TD Learning Jung Tobias1 and Polani Daniel2
• University of Hertfordshire Dept. of Computer Science
• Game Theory Social Intelligence
• University of Hertfordshire Dept. of Computer Science
• 1 ein Vortrag von Felix Dollinger Vorhersagende
• Artificial Intelligence Fuzzy Logic --An Appetizer
• Measuring Informational Distances Between Sensors and Sensor Integration Lars Olsson
• Constructive Artificial Intelligence Recursion, Examples and Exercises
• A Decentralized Agent-Based Platform for Automated Trade and its Simulation
• A Direct Approach to Robot Soccer Agents: Description for the Team
• An Information-Theoretic Approach for the Quanti cation of Relevance
• Survival strategies for AntLike Agents in a Competitive
• Artificial Intelligence Decision and Information
• From Infotaxis to Boids-like Swarm Behaviour Christoph Salge1
• Two Agents Acting as One Malte Harder1
• What do You Want to do Today? Relevant-Information Bookkeeping in Goal-Oriented Behaviour
• Hierarchical Behaviours: Getting the Most Bang for your Bit
• Impoverished Empowerment: `Meaningful' Action Sequence Generation through Bandwidth
• Adaptation of the Perception-Action Loop Using Active Channel Philippe Capdepuy1
• Emergence of Genetic Coding: an Information-theoretic Model
• A Simple Modularity Measure for Search Spaces based on Information Theory Peter Dauscher1, Daniel Polani2, Richard A. Watson3
• Empowerment: A Universal Agent-Centric Measure of Control Alexander S. Klyubin
• On a Quantitative Measure for Modularity Based on Information Theory
• Discovering Motion Flow by Temporal-Informational Correlations in Sensors
• Sensor Adaptation and Development in Robots by Entropy Maximization of Sensory Data
• Organization of the Information Flow in the Perception-Action Loop of Evolved Agents
• Sensory Channel Grouping and Structure from Uninterpreted Sensor Data Lars Olsson, Chrystopher L. Nehaniv, and Daniel Polani
• Quick Reference for XGrabtor 0.33 Daniel Polani
• Information: Whrung des Lebens Sommerakademie Olang, September 2008
• Aufgabenstellung Muster-/ Strukturerkennung
• Tobias Kerscher Nichtlineare Dynamik
• Reaktions-Diffusions-Systeme Jan Krieger, Sommerakademie Ftan 2004
• Selbstorganisierte Kritikalitt Self-organized Criticality (SOC)
• Constructive Artificial Intelligence Programming in Python
• Constructive Artificial Intelligence Heuristic Search and Games
• Constructive Artificial Intelligence Probability
• Introduction into Python Python 2: Programming, Control Structures,
• University of Hertfordshire Dept. of Computer Science
• University of Hertfordshire Dept. of Computer Science
• Advanced Symbolic Artificial Intelligence
• Artificial Intelligence Advanced Search
• Artificial Intelligence Daniel Polani
• Multiagent Systems well-defined interfaces
• Utility Theory Social Intelligence
• Markovian Decision Processes (MDP) Daniel Polani
• Market Simulation Social Intelligence
• Information Theory Daniel Polani
• University of Hertfordshire Dept. of Computer Science
• University of Hertfordshire Dept. of Computer Science
• University of Hertfordshire Dept. of Computer Science
• University of Hertfordshire Dept. of Computer Science
• Theoretische Grundlagen Dynamischer Systeme
• Origins of Scaling in Genetic Code Oliver Obst1,
• University of Hertfordshire Dept. of Computer Science
• University of Hertfordshire Dept. of Computer Science
• Constructive Artificial Intelligence Information Theory
• From Unknown Sensors and Actuators to Actions Grounded in Sensorimotor Perceptions
• Epsilon-Maschinen und Information Bottlenecks
• Der Satz von Godel 1 Marc Oliver Hoge
• Operator Notation Consider: 2 * a + b * c
• Measuring Self-Organization via Observers Daniel Polani
• Introduction into Python Python 5: Classes, Exceptions, Generators and more
• On the Emergence of Possession Norms in Agent Societies Felix Flentge 1
• Prolog Structures Structures
• Grundlagen der Informationstheorie
• University of Hertfordshire Dept. of Computer Science
• Constructive Artificial Intelligence Daniel Polani
• Organization of the Information Flow in the PerceptionAction Loop of Evolved Agents
• A virtual testbed for analysis and design of sensorimotoric aspects of agent control
• Information Theory: Motivation Task: sending data over a (possibly noisy) chan-
• Fitness Functions for the Optimization of SelfOrganizing Maps Daniel Polani
• Constructive Artificial Intelligence Probabilistic Inference
• All Else Being Equal Be Empowered Alexander S. Klyubin, Daniel Polani, and Chrystopher L. Nehaniv
• Tracking Information Flow through the Environment: Simple Cases of Stigmergy
• Multiagent Systems well-de ned interfaces
• A Framework for Sensor Evolution in a Population of Braitenberg Vehiclelike Agents
• RoboCup: Robot Soccer The Challenge of the 21st Century
• University of Hertfordshire Dept. of Computer Science
• Polani, D., (2011). An Informational Perspective on How the Em-bodiment Can Relieve Cognitive Burden. In Proc. IEEE Sympo-
• Harder, M., Polani, D., and Nehaniv, C. L., (2011). Think Globally, Sense Locally: From Local Information to Global Features. In
• van Dijk, S., and Polani, D., (2011). Look-Ahead Relevant In-formation: Reducing Cognitive Burden over Prolonged Tasks. In
• Obst, O., Polani, D., and Prokopenko, M., (2011). Origins of Scal-ing in Genetic Code. In Kampis, G., Karsai, I., and Szathmary, E.,
• Salge, C., and Polani, D., (2011). Local Information Maximisation creates Emergent Flocking Behaviour. In Lenaerts, T., Giacobini,
• van Dijk, S., and Polani, D., (2011). Grounding Subgoals in In-formation Transitions. In Proc. IEEE Symposium Series in Com-