Corpus ID: 43840115

Discovering hierarchy in reinforcement learning

@inproceedings{Hengst2003DiscoveringHI,
  title={Discovering hierarchy in reinforcement learning},
  author={B. Hengst},
  year={2003}
}
  • B. Hengst
  • Published 2003
  • Mathematics, Computer Science
This thesis addresses the open problem of automatically discovering hierarchical structure in reinforcement learning. Current algorithms for reinforcement learning fail to scale as problems become more complex. Many complex environments empirically exhibit hierarchy and can be modelled as interrelated subsystems, each in turn with hierarchic structure. Subsystems are often repetitive in time and space, meaning that they reoccur as components of different tasks or occur multiple times in… Expand
23 Citations
Automatic Discovery and Transfer of MAXQ Hierarchies in a Complex System
  • H. Wang, W. Li, X. Zhou
  • Computer Science
  • 2012 IEEE 24th International Conference on Tools with Artificial Intelligence
  • 2012
  • 2
Autonomous Extraction of a Hierarchical Structure of Tasks in Reinforcement Learning, A Sequential Associate Rule Mining Approach
  • 2
  • Highly Influenced
  • PDF
Hierarchical Reinforcement Learning: Assignment of Behaviours to Subpolicies by Self-Organization
  • 9
  • PDF
Simultaneously learning at different levels of abstraction
  • 7
Multi-Agent Hierarchical Reinforcement Learning by Integrating Options into MAXQ
  • 8
Safe State Abstraction and Reusable Continuing Subtasks in Hierarchical Reinforcement Learning
  • B. Hengst
  • Computer Science
  • Australian Conference on Artificial Intelligence
  • 2007
  • 10
  • PDF
Graph-Based Skill Acquisition For Reinforcement Learning
  • 6
...
1
2
3
...

References

SHOWING 1-10 OF 81 REFERENCES
Generating Hierarchical Structure in Reinforcement Learning from State Variables
  • B. Hengst
  • Mathematics, Computer Science
  • PRICAI
  • 2000
  • 22
  • PDF
Reinforcement Learning with a Hierarchy of Abstract Models
  • 132
Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition
  • 1,326
  • Highly Influential
  • PDF
Temporal abstraction in reinforcement learning
  • 255
Hierarchical reinforcement learning: a hybrid approach
  • 22
  • PDF
Tree based hierarchical reinforcement learning
  • 28
  • PDF
Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks
  • 82
  • Highly Influential
  • PDF
Concurrent layered learning
  • 56
  • PDF
Hierarchical control and learning for markov decision processes
  • 261
  • Highly Influential
Autonomous Discovery of Abstractions through Interaction with an Environment
  • 47
...
1
2
3
4
5
...