Corpus ID: 21385168

Leveraging attention focus for effective reinforcement learning in complex domains

@inproceedings{Rus2013LeveragingAF,
  title={Leveraging attention focus for effective reinforcement learning in complex domains},
  author={Luis Carlos Cobo Rus},
  year={2013}
}
IONS FOR REINFORCEMENT LEARNING Abstraction is one of the most common ways of scaling up reinforcement learning, along with function approximation and often overlapping with it. There is a rich and varied literature on the topic, going from state-space abstractions that clump similar states together to hierarchical approaches that define either temporally-extended actions or task subdivisions. This chapter reviews previous RL abstraction approaches so we can later position our attention focus… Expand

References

SHOWING 1-10 OF 84 REFERENCES
Recent Advances in Hierarchical Reinforcement Learning
  • 695
  • PDF
A survey of reinforcement learning in relational domains
  • 68
  • PDF
Learning Options in Reinforcement Learning
  • 237
  • PDF
The utility of temporal abstraction in reinforcement learning
  • 60
  • PDF
Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning
  • 2,378
  • PDF
Automatic task decomposition and state abstraction from demonstration
  • 22
  • Highly Influential
  • PDF
Automatic Induction of MAXQ Hierarchies
  • 5
  • PDF
Q-Decomposition for Reinforcement Learning Agents
  • 126
  • PDF
Dynamic abstraction in reinforcement learning via clustering
  • 203
  • PDF
Combining manual feedback with subsequent MDP reward signals for reinforcement learning
  • 187
  • PDF
...
1
2
3
4
5
...