Transfer of samples in batch reinforcement learning

@inproceedings{Lazaric2008TransferOS,
  title={Transfer of samples in batch reinforcement learning},
  author={Alessandro Lazaric and Marcello Restelli and Andrea Bonarini},
  booktitle={ICML},
  year={2008}
}
The main objective of transfer in reinforcement learning is to reduce the complexity of learning the solution of a target task by effectively reusing the knowledge retained from solving a set of source tasks. In this paper, we introduce a novel algorithm that transfers samples (i.e., tuples ⟨s, a, s', r⟩) from source to target tasks. Under the assumption that tasks have similar transition models and reward functions, we propose a method to select samples from the source tasks that are mostly… CONTINUE READING

Figures, Tables, and Topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 73 CITATIONS

Transfer learning by prototype generation in continuous spaces

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Autonomous Selection of Inter-Task Mappings in Transfer Learning (extended abstract)

  • AAAI Spring Symposium: Lifelong Machine Learning
  • 2013
VIEW 4 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Bayesian MultiTask Reinforcement Learning

  • 2010
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Knowledge Transfer in Reinforcement Learning Agent

  • 2019 International Conference on Information Technologies (InfoTech)
  • 2019
VIEW 2 EXCERPTS
CITES BACKGROUND & METHODS

FILTER CITATIONS BY YEAR

2008
2019

CITATION STATISTICS

  • 7 Highly Influenced Citations

  • Averaged 9 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-2 OF 2 REFERENCES