Corpus ID: 8121626

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

@article{Finn2016GuidedCL,
  title={Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization},
  author={Chelsea Finn and S. Levine and P. Abbeel},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.00448}
}
  • Chelsea Finn, S. Levine, P. Abbeel
  • Published 2016
  • Computer Science, Mathematics
  • ArXiv
  • Reinforcement learning can acquire complex behaviors from high-level specifications. [...] Key Method Our method addresses two key challenges in inverse optimal control: first, the need for informative features and effective regularization to impose structure on the cost, and second, the difficulty of learning the cost function under unknown dynamics for high-dimensional continuous systems.Expand Abstract

    Paper Mentions

    Nonparametric Inverse Reinforcement Learning and Approximate Optimal Control with Temporal Logic Tasks
    Inverse KKT: Learning cost functions of manipulation tasks from demonstrations
    24
    Deep Inverse Q-learning with Constraints
    Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
    123
    Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
    178
    Overcoming Exploration in Reinforcement Learning with Demonstrations
    208
    Learning manipulation skills from a single demonstration
    12

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES
    Direct Loss Minimization Inverse Optimal Control
    35
    Graph-Based Inverse Optimal Control for Robot Manipulation
    18
    Learning to search: Functional gradient techniques for imitation learning
    181
    Learning objective functions for manipulation
    87
    Learning contact-rich manipulation skills with guided policy search
    212
    Relative Entropy Inverse Reinforcement Learning
    216
    Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics
    318
    Apprenticeship learning via inverse reinforcement learning
    1897
    Maximum margin planning
    511
    Continuous Inverse Optimal Control with Locally Optimal Examples
    197