Corpus ID: 11669887

Concurrent Discovery of Task Hierarchies

@inproceedings{Potts2004ConcurrentDO,
  title={Concurrent Discovery of Task Hierarchies},
  author={D. Potts and B. Hengst},
  year={2004}
}
Task hierarchies can be used to decompose an intractable problem into smaller more manageable tasks. This paper explores how task hierarchies can model a domain for control purposes, and 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… Expand
4 Citations
Discovering hierarchy in reinforcement learning
  • 23
  • PDF
Graph-Based Skill Acquisition For Reinforcement Learning
  • 6

References

SHOWING 1-10 OF 19 REFERENCES
Learning Hierarchical Control Structures for Multiple Tasks and Changing Environments
  • 58
Generating Hierarchical Structure in Reinforcement Learning from State Variables
  • B. Hengst
  • Mathematics, Computer Science
  • PRICAI
  • 2000
  • 22
  • PDF
Concurrent layered learning
  • 56
  • PDF
Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition
  • 1,326
  • Highly Influential
  • PDF
Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks
  • 82
  • PDF
Discovering Hierarchy in Reinforcement Learning with HEXQ
  • 226
  • PDF
Layered Learning in Multiagent Systems
  • 268
Teleo-Reactive Programs for Agent Control
  • N. Nilsson
  • Computer Science
  • J. Artif. Intell. Res.
  • 1994
  • 419
  • PDF
Decision-Theoretic Planning: Structural Assumptions and Computational Leverage
  • 1,220
  • PDF
Layered learning in multiagent systems - a winning approach to robotic soccer
  • P. Stone
  • Engineering, Computer Science
  • Intelligent robotics and autonomous agents
  • 2000
  • 340
  • PDF
...
1
2
...