Fibonacci heaps and their uses in improved network optimization algorithms
Journal of the ACM (JACM)
Ten lectures on wavelets
Regularization theory and neural networks architectures
Neural Computation
Self-organizing maps
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Statistical Learning for Humanoid Robots
Autonomous Robots
Eligibility Traces for Off-Policy Policy Evaluation
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Least-squares policy iteration
The Journal of Machine Learning Research
Computing the shortest path: A search meets graph theory
SODA '05 Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms
Reinforcement learning with Gaussian processes
ICML '05 Proceedings of the 22nd international conference on Machine learning
Proto-value functions: developmental reinforcement learning
ICML '05 Proceedings of the 22nd international conference on Machine learning
Learning state-action basis functions for hierarchical MDPs
Proceedings of the 24th international conference on Machine learning
Adaptive importance sampling with automatic model selection in value function approximation
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3
Human Age Estimation by Metric Learning for Regression Problems
EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Metric Learning for Regression Problems and Human Age Estimation
PCM '09 Proceedings of the 10th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Improving Gaussian process value function approximation in policy gradient algorithms
ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
| Hi-index | 0.00 |
The least-squares policy iteration approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in real-world reinforcement learning tasks. In this paper, we propose a new basis function based on geodesic Gaussian kernels, which exploits the non-linear manifold structure induced by the Markov decision processes. The usefulness of the proposed method is successfully demonstrated in simulated robot arm control and Khepera robot navigation.