Transfer of samples in batch reinforcement learning

@inproceedings{Lazaric2008TransferOS,
  title={Transfer of samples in batch reinforcement learning},
  author={A. Lazaric and Marcello Restelli and Andrea Bonarini},
  booktitle={ICML '08},
  year={2008}
}
  • A. Lazaric, Marcello Restelli, Andrea Bonarini
  • Published in ICML '08 2008
  • Computer Science
  • 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
    109 Citations

    Figures, Tables, and Topics from this paper

    Explore Further: Topics Discussed in This Paper

    Importance Weighted Transfer of Samples in Reinforcement Learning
    • 16
    • PDF
    Transferring task models in Reinforcement Learning agents
    • 21
    • PDF
    Transferring Models in Hybrid Reinforcement Learning Agents
    • 3
    • PDF
    Transfer in Reinforcement Learning: A Framework and a Survey
    • A. Lazaric
    • Computer Science
    • Reinforcement Learning
    • 2012
    • 150
    • PDF
    Sequential Transfer in Reinforcement Learning with a Generative Model
    • 1
    • PDF
    REPAINT: Knowledge Transfer in Deep Actor-Critic Reinforcement Learning
    • PDF
    Learning Inter-Task Transferability in the Absence of Target Task Samples
    • 27
    • PDF
    Transfer Learning for continuous State and Action Spaces
    • 1
    • PDF
    A survey of transfer learning methods for reinforcement learning
    • 1
    • Highly Influenced

    References

    SHOWING 1-2 OF 2 REFERENCES
    Tree-Based Batch Mode Reinforcement Learning
    • 819
    • Highly Influential
    • PDF
    Transfer Learning via Inter-Task Mappings for Temporal Difference Learning
    • 202
    • Highly Influential
    • PDF