Corpus ID: 11017617

Relational State Abstractions for Reinforcement Learning

@inproceedings{Morales2004RelationalSA,
  title={Relational State Abstractions for Reinforcement Learning},
  author={E. Morales},
  year={2004}
}
Abstract Reinforcement learning deals with learningoptimal or near optimal policies while inter-acting with an external environment. Theapplicability of reinforcement learning hasbeen limited by largesearchspacesand by itsinability to re-use previously learned policyon other, although similar, problems. A re-lational representation can be used to allevi-ate both problems. In particular, this papershows how a relational representation can beused to produce powerful abstractions whichcan signi… Expand
18 Citations
A survey of reinforcement learning in relational domains
  • 68
  • Highly Influenced
  • PDF
The Concept of Opposition and Its Use in Q-Learning and Q(lambda) Techniques
  • 4
Automatic discovery of concepts and actions
  • 2
  • PDF
Oppositional Reinforcement Learning with Applications
  • 1
Knowledge of opposite actions for reinforcement learning
  • M. Shokri
  • Mathematics, Computer Science
  • Appl. Soft Comput.
  • 2011
  • 16
A Learning Classifier System Approach to Relational Reinforcement Learning
  • 13
Knowledge Representation for Learning How to Evaluate Partial Plans
Learning to evaluate conditional partial plans
  • 4
  • PDF
Learning to evaluate conditional partial plans
  • 6
...
1
2
...

References

SHOWING 1-10 OF 19 REFERENCES
Scaling Up Reinforcement Learning with a Relational Representation
  • 32
Learning to fly by combining reinforcement learning with behavioural cloning
  • 39
  • PDF
Relational Reinforcement Learning
  • 147
  • PDF
Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition
  • 1,327
  • PDF
Reinforcement Learning with Soft State Aggregation
  • 314
  • PDF
PAL: A Pattern-Based First-Order Inductive System
  • 26
  • PDF
On learning how to play
  • 6
Behavioural Cloning: Phenomena, Results and Problems
  • 30
...
1
2
...