Episodic task learning in Markov decision processes

@article{Lin2011EpisodicTL,
  title={Episodic task learning in Markov decision processes},
  author={Yong Lin and F. Makedon and Yurong Xu},
  journal={Artificial Intelligence Review},
  year={2011},
  volume={36},
  pages={87-98}
}
Hierarchical algorithms for Markov decision processes have been proved to be useful for the problem domains with multiple subtasks. Although the existing hierarchical approaches are strong in task decomposition, they are weak in task abstraction, which is more important for task analysis and modeling. In this paper, we propose a task-oriented design to strengthen the task abstraction. Our approach learns an episodic task model from the problem domain, with which the planner obtains the same… Expand
1 Citations

References

SHOWING 1-10 OF 11 REFERENCES
Exploiting Structure in Policy Construction
  • 442
  • PDF
A causal approach to hierarchical decomposition of factored MDPs
  • 38
  • PDF
Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition
  • 1,326
  • PDF
Synthesis of Hierarchical Finite-State Controllers for POMDPs
  • 56
  • Highly Influential
  • PDF
Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning
  • 2,378
  • PDF
The MAXQ Method for Hierarchical Reinforcement Learning
  • 319
  • PDF
Discovering multiple levels of a task hierarchy concurrently
  • 3
Discovering Hierarchy in Reinforcement Learning with HEXQ
  • 226
  • Highly Influential
  • PDF
Hierarchical Knowledge-Based Process Planning in Manufacturing
  • 8
  • PDF
Heuristic Search Value Iteration for POMDPs
  • 459
  • Highly Influential
  • PDF
...
1
2
...