Department of Engineering Computational and Biological Learning Lab

Selected Talks

2009

1. 2009-11-23: "Filtering (and Smoothing) in Gaussian Process Dynamic Systems", Machine Learning and Optimisation Group, University of Manchester, UK.
   [slides]
2. 2009-09-23: "Efficient Reinforcement Learning for Motor Control", 10th International Workshop on Systems and Control, Hluboka nad Vltavou, Czech Republic. Best presentation award
   [slides] [link]
3. 2009-07-29: "Efficient Reinforcement Learning for Motor Control", Statistical Machine Learning and Motor Control Group, University of Edinburgh, UK
4. 2009-06-26: "Probabilistic Inference for Efficient Learning in Control", Robotics Institute, CMU, Pittsburgh, PA, USA
5. 2009-06-24: "Probabilistic Inference for Efficient Learning in Control", Robust Robotics Group, MIT, Cambridge, MA, USA
   [link]
   
6. 2009-06-23: "Probabilistic Inference for Efficient Learning in Control", Reasoning and Learning Lab, McGill University, Montreal, Canada
7. 2009-06-15: "Analytic Moment-based Gaussian Process Filtering", International Conference on Machine Learning, Montreal, Canada
   [slides]
8. 2009-06-08: "Bayesian Inference for Efficient Learning in Control", Gatsby Computational Neuroscience Unit, University College London, UK
9. 2009-05-08: "Probabilistic Inference for Fast Learning in Control", CSML Seminar, University College London, UK
   [link] [demos]
10. 2009-04-29: "Probabilistic Models for Fast Learning in Control", Dagstuhl Seminar Sampling-based Optimization in the Presence of Uncertainty, Dagstuhl, Germany
    [slides] [link] [demos]
11. 2009-01-02: "Probabilistic Modeling for Efficient Learning in Control", Department of Biomedical Engineering and Computational Science, Helsinki University of Technology, Finland
    [slides]

2008

1. 2008-10-10: "Bayesian Models for Fast Learning Control", Max Planck Institute for Biological Cybernetics, Tübingen, Germany
2. 2008-07-03: "Policy Optimization by Implicit Probabilistic Simulation", 8th European Workshop on Reinforcement Learning, Lille, France
   [slides] [link] [demos]
3. 2008-06-13: "Approximate Dynamic Programming with Gaussian Processes", 2008 American Control Conference, Seattle, WA, USA
   [slides] [link]
4. 2008-06-09: "Probabilistic Machine Learning for Control", Robotics and State Estimation Lab, University of Washington, Seattle, WA, USA
   [slides] [link]
5. 2008-04-23: "Model-Based Reinforcement Learning with Continuous States and Actions", 16th European Symposium on Artificial Neural Networks, Bruges, Belgium
   [slides] [link]
6. 2008-02-14: "Approximate Dynamic Programming with Gaussian Processes", CSML Seminar, University College London, UK
   [slides] [link]

2007

1. 2007-12-05: "Model-Based Reinforcement Learning with Gaussian Processes", Intelligent Sensor-Actuator-Systems Laboratory, Universität Karlsruhe (TH), Germany
2. 2007-11-26: "Reinforcement Learning with Gaussian Process Models", Max Planck Institute for Biological Cybernetics, Tübingen, Germany
3. 2007-11-16: "Introduction to Reinforcement Learning—MDP Case", CBL Lab Reinforcement Learning Day 2007, University of Cambridge, UK
   [slides] comment: the demo for value iteration is not good
4. 2007-11-07: "Optimal Control and Reinforcement Learning with Gaussian Process Models", CBL Lab, University of Cambridge, UK
   [link]
5. 2007-08-03: "GP World — Tutorial on Gaussian Processes and their Use in Reinforcement Learning", Workshop on Analytical Challenges in Reinforcement Learning, Tübingen, Germany
6. 2007-07-30: "Control and Reinforcement Learning", Workshop on Analytical Challenges in Reinforcement Learning, Tübingen, Germany
7. 2007-07-04: "Online-Computation Approach to Optimal Control of Noise-Affected Nonlinear Systems with Continuous State and Control Spaces", 9th European Control Conference (ECC 2007), Kos, Greece
   [slides]
8. 2007-05-24: "What can Gaussian Processes do for Reinforcement Learning?", Department of Engineering, University of Cambridge, UK
   [link]

2006

1. 2006-09-25: "An Online-Computation Approach to Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems", Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany
   [link]
2. 2006-09-21: "An Online-Computation Approach to Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems", Intelligent Sensor-Actuator-Systems Laboratory, Universität Karlsruhe (TH), Karlsruhe, Germany
3. 2006-09-14: "An Online-Computation Approach to Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems", Department of Information Technology and Electrical Engineering, Wearable Computing Laboratory, ETH Zürich, Zürich, Switzerland
4. 2006-09-11: "An Online-Computation Approach to Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems", Department of Empirical Inference for Machine Learning and Perception, Max Planck Institute for Biological Cybernetics, Tübingen, Germany
5. 2006-09-08: "An Online-Computation Approach to Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems", Lehrstuhl für Automatisierungstechnik/Regelungstechnik, Bergische Universität Wuppertal, Wuppertal, Germany
6. 2006-09-05: "Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems Based on a Minimum Principle", 6th IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2006), Heidelberg, Germany
   [slides]
7. 2006-07-05: "An Approach to Optimal Control of Stochastic Nonlinear Systems", Systems and Control Laboratory, Kanazawa University, Kanazawa, Japan
8. 2006-07-04: "An Approach to Optimal Control of Stochastic Nonlinear Systems", Fujita Laboratory, Tokyo Institute of Technology, Tokyo, Japan
9. 2006-06-30: "An Approach to Optimal Control of Stochastic Nonlinear Systems", Machine Control Laboratory, Osaka University, Osaka, Japan