A-Learning for Approximate Planning

@inproceedings{Blatt2004ALearningFA,
  title={A-Learning for Approximate Planning},
  author={Doron Blatt and Suzan A. Murphy},
  year={2004}
}
Abstract We consider a new algorithm for reinforcement learning called A-learning. A-learning learns the advantages from a single training set. We compare A-learning with function approximation to Q-learning with function approximation and find that because A-learning approximates only the advantages it is less likely to exhibit bias due to the function approximation as compared to Q-learning.We consider a new algorithm for reinforcement learning called A-learning. A-learning learns the… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.
11 Citations
10 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 11 extracted citations

Similar Papers

Loading similar papers…