Corpus ID: 202712580

Meta-Inverse Reinforcement Learning with Probabilistic Context Variables

  title={Meta-Inverse Reinforcement Learning with Probabilistic Context Variables},
  author={Lantao Yu and Tianhe Yu and Chelsea Finn and S. Ermon},
  • Lantao Yu, Tianhe Yu, +1 author S. Ermon
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • Reinforcement learning demands a reward function, which is often difficult to provide or design in real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations, several major challenges remain. First, existing IRL methods learn reward functions from scratch, requiring large numbers of demonstrations to correctly infer the reward for each task the agent may need to perform. Second, and more subtly, existing… CONTINUE READING
    5 Citations

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks
    Multi-agent Adversarial Inverse Reinforcement Learning with Latent Variables
    • 2
    • PDF
    Hyper-Meta Reinforcement Learning with Sparse Reward
    The MAGICAL Benchmark for Robust Imitation
    Path Planning using Neural A* Search


    Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
    • 21
    • PDF
    Learning Robust Rewards with Adversarial Inverse Reinforcement Learning
    • 204
    • PDF
    Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
    • 113
    • PDF
    Multi-task Maximum Entropy Inverse Reinforcement Learning
    • 11
    • Highly Influential
    • PDF
    Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
    • 435
    • PDF
    Learning an Embedding Space for Transferable Robot Skills
    • 135
    Apprenticeship learning via inverse reinforcement learning
    • 1,975
    • PDF
    RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
    • 385
    • PDF
    Generative Adversarial Imitation Learning
    • 876
    • PDF