Using expectation-maximization for reinforcement learning
Neural Computation
Robot Dynamics Algorithm
Scalable Techniques from Nonparametric Statistics for Real Time Robot Learning
Applied Intelligence
Introduction to Stochastic Search and Optimization
Introduction to Stochastic Search and Optimization
MOSAIC Model for Sensorimotor Learning and Control
Neural Computation
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Learning to Control in Operational Space
International Journal of Robotics Research
Episodic Reinforcement Learning by Logistic Reward-Weighted Regression
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Fitness Expectation Maximization
Proceedings of the 10th international conference on Parallel Problem Solving from Nature: PPSN X
Efficient Sample Reuse in EM-Based Policy Search
ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part I
Reinforcement learning to adjust robot movements to new situations
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
Hi-index | 0.00 |
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-base reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.