Corpus ID: 13973870

Robust Bayesian Inverse Reinforcement Learning with Sparse Behavior Noise

@inproceedings{Zheng2014RobustBI,
  title={Robust Bayesian Inverse Reinforcement Learning with Sparse Behavior Noise},
  author={Jiangchuan Zheng and S. Liu and L. Ni},
  booktitle={AAAI},
  year={2014}
}
  • Jiangchuan Zheng, S. Liu, L. Ni
  • Published in AAAI 2014
  • Computer Science
    • Inverse reinforcement learning (IRL) aims to recover the reward function underlying a Markov Decision Process from behaviors of experts in support of decision-making. Most recent work on IRL assumes the same level of trustworthiness of all expert behaviors, and frames IRL as a process of seeking reward function that makes those behaviors appear (near)- optimal. However, it is common in reality that noisy expert behaviors disobeying the optimal policy exist, which may degrade the IRL performance… CONTINUE READING
    View Paper
    aaai.org
    37 Citations
    Background Citations
    20
    Methods Citations
    12
    37 Citations
    Citation Type

    Citation Type

    CWAE-IRL: Formulating a supervised approach to Inverse Reinforcement Learning problem
    • PDF
    Bayesian Robust Optimization for Imitation Learning
    • PDF
    Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning
    • 18
    • PDF
    Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
    • 52
    • PDF
    Active Learning from Critiques via Bayesian Inverse Reinforcement Learning
    • 2
    • PDF
    Active Reward Learning from Critiques
    • Yuchen Cui, S. Niekum
    • Computer Science
    • 2018 IEEE International Conference on Robotics and Automation (ICRA)
    • 2018
    • 24
    • PDF
    On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
    • 4
    • PDF
    Inverse Reinforcement Learning From Like-Minded Teachers
    • 1
    • PDF
    Inverse Reinforcement Learning from Failure
    • 48
    • PDF
    Combination of learning from non-optimal demonstrations and feedbacks using inverse reinforcement learning and Bayesian policy improvement
    • 1

    References

    SHOWING 1-10 OF 28 REFERENCES
    Maximum Entropy Inverse Reinforcement Learning
    • 1,477
    • Highly Influential
    • PDF
    Bayesian Inverse Reinforcement Learning
    • 486
    • Highly Influential
    • PDF
    Apprenticeship learning via inverse reinforcement learning
    • 2,018
    • PDF
    Active Learning for Reward Estimation in Inverse Reinforcement Learning
    • 153
    • PDF
    Inverse Reinforcement Learning with PI 2
    • 9
    • PDF
    Nonlinear Inverse Reinforcement Learning with Gaussian Processes
    • 235
    • PDF
    Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods
    • 202
    • PDF
    Bayesian Multitask Inverse Reinforcement Learning
    • 76
    • PDF
    Maximum margin planning
    • 536
    • PDF
    Supervised Probabilistic Robust Embedding with Sparse Noise
    • 1
    • PDF