Q-Cut - Dynamic Discovery of Sub-goals in Reinforcement Learning
ECML '02 Proceedings of the 13th European Conference on Machine Learning
Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Learning Options in Reinforcement Learning
Proceedings of the 5th International Symposium on Abstraction, Reformulation and Approximation
Dynamic abstraction in reinforcement learning via clustering
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Identifying useful subgoals in reinforcement learning by local graph partitioning
ICML '05 Proceedings of the 22nd international conference on Machine learning
Hi-index | 0.00 |
This paper proposes a learning method which can discover the subgoals on the different state subspaces. It uses the improved fuzzy c-means clustering algorithm to classify the state spaces firstly, and then uses the unique direction value to find the set of subgoals, and finally creates the set of options. The experimental result shows that it can discover the subgoals automatically and quickly. This method can be adapted to the learning tasks under the dynamic audio-visual environment.