BibSonomy :: user  :: schaul ::

bookmarks

publications

(9)   

• Policy gradient methods for robotics
  J. Peters and S. Schaal Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Beijing, China, (2006)
  to gradients, daanbib, robotics policy, reinforcement, learning, by schaul and 2 other people on Feb 26, 2008, 11:58 AM
  BibTeX 
• Defensive Universal Learning with Experts
  J. Poland and M. Hutter Proc. 16th International Conf. on Algorithmic Learning Theory (ALT'05), volume3734ofLNAI, page356--370. Singapore, Springer, Berlin, (2005)
  to with game, universal, asymptotic, juergen, learning, optimality, bandits, environments, observation, expert, prediction, partial, advice, responsive, by schaul and 3 other people on Feb 26, 2008, 11:58 AM
  URL | BibTeX 
• Master Algorithms for Active Experts Problems based on Increasing Loss Values
  J. Poland and M. Hutter Annual Machine Learning Conference of Belgium and the Netherlands (Benelearn-2005), Enschede, (2005)
  to optimality, advice, game, with universal, observation, learning, responsive, expert, environments, juergen, partial, asymptotic, bandits, prediction, by schaul and 2 other people on Feb 26, 2008, 11:58 AM
  URL | BibTeX 
• Strong Asymptotic Assertions for Discrete MDL in Regression and Classification
  J. Poland and M. Hutter Annual Machine Learning Conference of Belgium and the Netherlands (Benelearn-2005), Enschede, (2005)
  to model, regression, sequence prediction, classification, discrete, bayes, length, juergen, learning, description, minimum, machine, convergence, marginalization, mixture, classes, by schaul and 2 other people on Feb 26, 2008, 11:58 AM
  URL | BibTeX 
• Adaptive Online Prediction by Following the Perturbed Leader
  M. Hutter and J. Poland Journal of Machine Learning Research(2005)
  to sequential, hierarchy, follow, alphabet, general, perturbed, loss, rate, probability, the, adversary, high, and, leader, prediction, with experts, weights, expert, bounds, advice, adaptive, online, expected, learning, of, juergen, by schaul and 3 other people on Feb 26, 2008, 11:58 AM
  URL | BibTeX 
• Prediction with Expert Advice by Following the Perturbed Leader for General Weights
  M. Hutter and J. Poland Proc. 15th International Conf. on Algorithmic Learning Theory (ALT'04), volume3244ofLNAI, page279--293. Padova, Springer, Berlin, (2004)
  to juergen, with online, follow, general, hierarchy, of, perturbed, sequential, learning, loss, alphabet, rate, weights, high, the, prediction, leader, adaptive, expected, probability, experts, and, expert, bounds, advice, by schaul and 3 other people on Feb 26, 2008, 11:58 AM
  URL | BibTeX 
• Market-Based Reinforcement Learning in Partially Observable Worlds
  Ivo Kwee and Marcus Hutter and Juergen Schmidhuber Proc. International Conf. on Artificial Neural Networks (ICANN-2001), volume2130ofLNCS, page865--873. Vienna, Springer, Berlin, (2001)
  to learning, partial, observable, hayek, system juergen, environment, reinforcement, by schaul and 3 other people on Feb 26, 2008, 11:58 AM
  URL | BibTeX 
• Gradient-based Reinforcement Planning in Policy-Search Methods
  Ivo Kwee and Marcus Hutter and Juergen Schmidhuber Proc. 5th European Workshop on Reinforcement Learning (EWRL-5), 27, page27--29. Onderwijsinsituut CKI, Utrecht Univ., (2001)
  to juergen, policy, gradient, decent, planning, learning, artificial, search intelligence, reinforcement, direct, by schaul and 2 other people on Feb 26, 2008, 11:58 AM
  URL | BibTeX 
• Universal Sequential Decisions in Unknown Environments
  M. Hutter Proc. 5th European Workshop on Reinforcement Learning (EWRL-5), 27, page25--26. Onderwijsinsituut CKI, Utrecht Univ., (2001)
  to decision, complexity, agents, universal induction, artificial, solomonoff, computational, theory, reinforcement, kolmogorov, learning, algorithmic, rational, juergen, sequential, probability, intelligence, by schaul and 1 other person on Feb 26, 2008, 11:58 AM
  URL | BibTeX