(:requiretuid:)

Topics for the Robot Learning Seminar

Die folgenden Themen werden von unterschiedlichen Betreuern angeboten. Beim Vorgespraech werden die Themen gemeinsam vergeben. Themen der eigenen Wahl - soweit im Rahmen des Seminars - sind zusaetzlich erlaubt.

DEADLINE FOR TOPIC SELECTION: MAY 1, 2013

A) Learning robot control, Difficulty: 1, Advisor: Jan Peters

  1. S. Schaal and C. G. Atkeson, Learning Control in Robotics, IEEE Robotics & Automation Magazine, 17, 20-29, 2010 [paper]

B) Path-Integral Reinforcement Learning in Robotics, Difficulty: 5, Advisor: Jan Peters

  1. Theodorou E, Buchli J, and Schaal S (2010). A Generalized Path Integral Control Approach to Reinforcement Learning, Journal of Machine Learning Research,11, pp.3137-3181
  2. Norikazu Sugimoto and Jun Morimoto (2011), Phase-dependent Trajectory Optimization for CPG-based Biped Walking Using Path Integral Reinforcement Learning, IEEE-RAS International Conference on Humanoid Robots (Humaniods 2011), pp. 255-206, Bled, Slovenia

C) Hierarchical Reinforcement Learning in Robot Control, Difficulty: 3, Advisor: Jan Peters

  1. Jun Morimoto and Kenji Doya (2001), Acquisition of Stand-up Behavior by a Real Robot using Hierarchical Reinforcement Learning, Robotics and Autonomous Systems, Volume 36, Issue 1, pages 37-51, 2001
  2. Jun Morimoto and Kenji Doya (1998), Hierarchical reinforcement learning for motion learning: Learning "Stand-up" Trajectories, Advanced Robotics, Volume 13, Number 3, pages 267-268, 1998
  3. Freek Stulp and Stefan Schaal. Hierarchical Reinforcement Learning with Motion Primitives. In 11th IEEE-RAS International Conference on Humanoid Robots, 2011.

D) Human Motion Segmentation and Prediction, Difficulty: 3, Advisor: Heni Ben Amor

  1. F. Zhou et al.: Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion, IEEE Transactions Pattern Analysis and Machine Intelligence (PAMI), 2013.
  2. S. Hauberg et al.: Predicting Articulated Human Motion from Spatial Processes, In International Journal of Computer Vision (IJCV), 2011.

E) Spectral Embeddings, Difficulty: 5, Advisor: Marc Deisenroth

  1. Boots et al.: Hilbert Space Embeddings of Hidden Markov Models, ICML 2010.
  2. Boots and Gordon: An Online Spectral Learning Algorithm for Partially Observable Nonlinear Dynamical Systems, AAAI 2011.

F) Slice Sampling, Difficulty 4, Advisor: Marc Deisenroth

  1. Neal: Probabilistic inference using Markov chain Monte Carlo methods, TechReport University of Toronto, 1993
  2. Murray: Advances in Markov chain Monte Carlo methods, PhD thesis, 2007.
  3. Murray et al.: Elliptical Slice Sampling, AISTATS, 2010.
  4. Nishihara et al.: Parallel MCMC with Generalized Elliptical Slice Sampling, 2012

G) Style-based Character Animation and Style Translation, Difficulty: 3, Advisor: Heni Ben Amor

  1. Matthew Brand and Aaron Hertzmann (2000), Style machines. In Proceedings of the 27th annual conference on Computer graphics and interactive techniques (SIGGRAPH '00), pp 183-192
  2. Eugene Hsu, Kari Pulli and Jovan Popovic '(2005), Style Translation for Human Motion, Computer Graphics and Interactive Techniques Conference (SIGRAPH 2005), Los Angeles, USA
  3. Yan Li, Tianshu Wang, and Heung-Yeung Shum (2002). Motion texture: a two-level statistical model for character motion synthesis. In Proceedings of the 29th annual conference on Computer graphics and interactive techniques (SIGGRAPH '02). pp 465-472

H) Approximate Inference for Motor Control, Difficulty 4, Advisor: Gerhard Neumann

  1. Marc Toussaint and Christian Goerick (2010), A Bayesian view on motor control and planning, From motor to interaction learning in robots, Studies in Computational Intelligence
  2. Marc Toussaint (2009), Robot Trajectory Optimization using Approximate Inference. 25th International Conference on Machine Learning

I) Hierarchical Bayesian Models, Difficulty 3, Advisor: Gerhard Neumann

  1. C. Kemp, A. Perfors, J. B. Tenenbaum (2007), Learning overhypotheses with hierarchical Bayesian models, Developmental Science 10
  2. David Wingate, Noah D. Goodman, Daniel M. Roy, Leslie P. Kaelbling and Joshua B. Tenenbaum (2011), Bayesian Policy Search with Policy Priors, International Joint Conference on Artificial Intelligence (IJCAI), 2011

J) Interaction Learning, Difficulty: 3, Advisor: Heni Ben Amor

  1. Brian D. Ziebart, J. Andrew Bagnell, and Anind K. Dey, Modeling Interaction via the Principle of Maximum Causal Entropy, In Proceedings of the International Conference on Machine Learning (ICML 2010), pp. 1255--1262, pdf
  2. Wampler, K. Andersen, E. Herbst, E. Lee, Y. Popović, Z., Character Animation in Two-Player Adversarial Games, ACM Transactions on Graphics 2010, Volume 29, website
  3. Hubert P. H. Shum, Taku Komura and Shuntaro Yamazaki, �Simulating Multiple Character Interactions with Collaborative and Adversarial Goals�, The 2010 IEEE Transactions on Visualization and Computer Graphics (TVCG),

K) Advances in Manifold Learning, Difficulty 4, Advisor: Heni Ben Amor

  1. K. Weinberger et al.:Unsupervised Learning of Image Manifolds by Semidefinite Programming, International Journal of Computer Vision, 2006.
  2. Chen et al.: Compressive Sensing on Manifolds Using a Nonparametric Mixture of Factor Analyzers:

Algorithm and Performance Bounds, IEEE Transactions on Signal Processing, 2010.

L) Inverse Optimal Control, Difficulty 4, Advisor: Gerhard Neumann

  1. Continuous Inverse Optimal Control with Locally Optimal Examples, Sergey Levine, Vladlen Koltun, In Proceedings of the International Conference on Machine Learning (ICML 2012), pdf
  2. Nonlinear Inverse Reinforcement Learning with Gaussian Processes, Sergey Levine, Zoran Popović, Vladlen Koltun, NIPS 2011,

pdf

M) Kernel Bayes Rule, Difficulty 5, Advisor: Gerhard Neumann

  1. Kernel Bayes' Rule, Kenji Fukumizu, Le Song, Arthur Gretton, NIPS 2011, pdf (longer version)