Discovering multiple levels of a task hierarchy concurrently
@article{Potts2004DiscoveringML, title={Discovering multiple levels of a task hierarchy concurrently}, author={D. Potts and B. Hengst}, journal={Robotics Auton. Syst.}, year={2004}, volume={49}, pages={43-55} }
Abstract Task hierarchies can be used to decompose an intractable problem into smaller more manageable tasks. This paper examines an existing algorithm (HEXQ) that automatically discovers a task hierarchy through interaction with the environment. The initial performance of the algorithm can be limited because it must adequately explore each level of the hierarchy before starting construction of the next, and it cannot adapt to a dynamic environment. The contribution of this paper is to present… Expand
Figures, Tables, and Topics from this paper
3 Citations
Episodic task learning in Markov decision processes
- Computer Science
- Artificial Intelligence Review
- 2011
- 1
References
SHOWING 1-10 OF 21 REFERENCES
Generating Hierarchical Structure in Reinforcement Learning from State Variables
- Mathematics, Computer Science
- PRICAI
- 2000
- 22
- PDF
Learning hierarchical control structures for multiple tasks and changing environments
- Computer Science
- 1998
- 88
- PDF
Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition
- Computer Science
- J. Artif. Intell. Res.
- 2000
- 1,328
- Highly Influential
- PDF
Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks
- Computer Science
- J. Artif. Intell. Res.
- 2002
- 82
- PDF
Decision-Theoretic Planning: Structural Assumptions and Computational Leverage
- Computer Science
- J. Artif. Intell. Res.
- 1999
- 1,220
- PDF