Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications

@article{Brown2019MachineTF,
  title={Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications},
  author={Daniel S. Brown and S. Niekum},
  journal={ArXiv},
  year={2019},
  volume={abs/1805.07687}
}
  • Daniel S. Brown, S. Niekum
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL, little work has been done to understand of the minimum set of demonstrations needed to teach a specific sequential decision-making task. We formalize the problem of finding optimal demonstrations for IRL as a machine teaching problem where the goal is to find the minimum number of demonstrations needed to specify the… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Interactive Teaching Algorithms for Inverse Reinforcement Learning
    19
    Class Teaching for Inverse Reinforcement Learners
    Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations
    2
    Assisted Inverse Reinforcement Learning
    1
    Ranking-Based Reward Extrapolation without Rankings
    3
    Machine Teaching of Active Sequential Learners
    7
    Adaptive Teaching of Temporal Logic Formulas to Learners with Preferences
    Using Causal Analysis to Learn Specifications from Task Demonstrations
    7

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 82 REFERENCES
    A survey of inverse reinforcement learning techniques
    34
    A survey of inverse reinforcement learning techniques
    34
    Inverse Reinforcement Learning through Policy Gradient Minimization
    13
    Active Learning from Critiques via Bayesian Inverse Reinforcement Learning
    2
    Bayesian Nonparametric Reward Learning From Demonstration
    32
    Apprenticeship learning via inverse reinforcement learning
    1896
    A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress
    41
    Analysis of Inverse Reinforcement Learning with Perturbed Demonstrations
    11