Hierarchical Learning in Stochastic Domains: Preliminary Results

@inproceedings{Kaelbling1993HierarchicalLI,
  title={Hierarchical Learning in Stochastic Domains: Preliminary Results},
  author={L. Kaelbling},
  booktitle={ICML},
  year={1993}
}
This paper presents the HDG learning algorithm, which uses a hierarchical decomposition of the state space to make learning to achieve goals more efficient with a small penalty in path quality. Special care must be taken when performing hierarchical planning and learning in stochastic domains, because macro-operators cannot be executed ballistically. The HDG algorithm, which is a descendent of Watkins' Q-learning algorithm, is described here and preliminary empirical results are presented. 
218 Citations
Self-segmentation of sequences
  • R. Sun, Chad Sessions
  • Computer Science
  • IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)
  • 1999
  • 4
Variable Resolution Hierarchical RL
  • 1
  • PDF
A hierarchical approach to efficient reinforcement learning in deterministic domains
  • 23
  • PDF
Multi-layered learning systems for vision-based behavior acquisition of a real mobile robot
  • 31
  • PDF
Finding Structure in Reinforcement Learning
  • 220
  • PDF
Multi-time Models for Temporally Abstract Planning
  • 132
  • PDF
Safe State Abstraction and Reusable Continuing Subtasks in Hierarchical Reinforcement Learning
  • B. Hengst
  • Computer Science
  • Australian Conference on Artificial Intelligence
  • 2007
  • 10
  • PDF
TD Models: Modeling the World at a Mixture of Time Scales
  • 164
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 27 REFERENCES
Reinforcement Learning with a Hierarchy of Abstract Models
  • 132
Learning to Achieve Goals
  • 165
Feudal Reinforcement Learning
  • 541
  • PDF
Learning and Sequential Decision Making
  • 305
The role of exploration in learning control
  • 230
Reinforcement learning for robots using neural networks
  • 794
  • PDF
A Role for Anticipation in Reactive Systems that Learn
  • 32
...
1
2
3
...