Corpus ID: 189928215

Personalized Apprenticeship Learning from Heterogeneous Decision-Makers

@article{Paleja2019PersonalizedAL,
  title={Personalized Apprenticeship Learning from Heterogeneous Decision-Makers},
  author={Rohan R. Paleja and Andrew Silva and M. Gombolay},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.06397}
}
  • Rohan R. Paleja, Andrew Silva, M. Gombolay
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • Human domain experts solve difficult planning problems by drawing on years of experience. In many cases, computing a solution to such problems is computationally intractable or requires encoding heuristics from human domain experts. As codifying this knowledge leaves much to be desired, we aim to infer their strategies through observation. The challenge lies in that humans exhibit heterogeneity in their latent decision-making criteria. To overcome this, we propose a personalized apprenticeship… CONTINUE READING
    2 Citations
    Coordinated Control of UAVs for Human-Centered Active Sensing of Wildfires
    • 4
    • PDF
    Coordinated Control of UAVs for Human-Centered Active Sensing of Wildfires

    References

    SHOWING 1-10 OF 30 REFERENCES
    Active Advice Seeking for Inverse Reinforcement Learning
    • 26
    • PDF
    Using Causal Analysis to Learn Specifications from Task Demonstrations
    • 8
    • PDF
    Apprenticeship learning via inverse reinforcement learning
    • 2,019
    • PDF
    Planning for Conjunctive Goals
    • D. Chapman
    • Mathematics, Computer Science
    • Artif. Intell.
    • 1987
    • 1,331
    • PDF
    Active Learning with Feedback on Features and Instances
    • 198
    Efficient Model Learning for Human-Robot Collaborative Tasks
    • 16
    • PDF
    Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior
    • 44
    • PDF
    StarCraft II: A New Challenge for Reinforcement Learning
    • 376
    • PDF
    Confidence-based policy learning from demonstration using Gaussian mixture models
    • 175
    • PDF