Search Machine Learning Repository:
All publications by Jan R. Peters
authors venues years



Model-Based Relative Entropy Stochastic Search
Abbas Abdolmaleki, Rudolf Lioutikov, Jan R. Peters, Nuno Lau, Luis P. Reis and Gerhard Neumann
Advances in Neural Information Processing Systems 28, 2015


Algorithms for Learning Markov Field Policies
Abdeslam Boularias, Jan R. Peters and Oliver B. Kroemer
Advances in Neural Information Processing Systems 25, 2012


Hierarchical Relative Entropy Policy Search
Christian Daniel, Gerhard Neumann and Jan R. Peters
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS-12), 2012


A Non-Parametric Approach to Dynamic Programming
Oliver B. Kroemer and Jan R. Peters
Advances in Neural Information Processing Systems 24, 2011


Relative Entropy Inverse Reinforcement Learning
Abdeslam Boularias, Jens Kober and Jan R. Peters
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS-11), 2011


Switched Latent Force Models for Movement Segmentation
Mauricio Alvarez, Jan R. Peters, Neil D. Lawrence and Bernhard Schölkopf
Advances in Neural Information Processing Systems 23, 2010


Movement extraction by detecting dynamics switches and repetitions
Silvia Chiappa and Jan R. Peters
Advances in Neural Information Processing Systems 23, 2010


Incremental Sparsification for Real-time Online Model Learning
Duy Nguyen-tuong and Jan R. Peters
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS-10), 2010


Learning complex motions by sequencing simpler motion templates
Gerhard Neumann, Wolfgang Maass and Jan R. Peters
Proceedings of the 26th International Conference on Machine Learning (ICML-09), 2009


An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward
Matthew D. Hoffman, Nando D. Freitas, Arnaud Doucet and Jan R. Peters
Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS-09), 2009


Fitted Q-iteration by Advantage Weighted Regression
Gerhard Neumann and Jan R. Peters
Advances in Neural Information Processing Systems 21, 2008


Using Bayesian Dynamical Systems for Motion Template Libraries
Silvia Chiappa, Jens Kober and Jan R. Peters
Advances in Neural Information Processing Systems 21, 2008


Local Gaussian Process Regression for Real Time Online Model Learning
Duy Nguyen-tuong, Jan R. Peters and Matthias Seeger
Advances in Neural Information Processing Systems 21, 2008


Policy Search for Motor Primitives in Robotics
Jens Kober and Jan R. Peters
Advances in Neural Information Processing Systems 21, 2008


Reinforcement learning by reward-weighted regression for operational space control
Jan R. Peters and Stefan Schaal
Proceedings of the 24th International Conference on Machine Learning (ICML-07), 2007