Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks

Preprint English OPEN
Thananjeyan, Brijen; Balakrishna, Ashwin; Rosolia, Ugo; Li, Felix; McAllister, Rowan; Gonzalez, Joseph E.; Levine, Sergey; Borrelli, Francesco; Goldberg, Ken;
(2019)
  • Subject: Statistics - Machine Learning | Computer Science - Machine Learning | Computer Science - Artificial Intelligence | Computer Science - Robotics
Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes it hard to enforce constraints during learning. We address these issues... View more
  • References (36)
    36 references, page 1 of 4

    Joshua Achiam et al. “Constrained policy optimization”. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org. 2017, pp. 22-31.

    Dario Amodei et al. “Concrete problems in AI safety”. In: arXiv preprint arXiv:1606.06565 (2016).

    Marcin Andrychowicz et al. “Hindsight Experience Replay”. In: Advances in Neural Information Processing Systems. 2017, pp. 5048-5058.

    Yusuf Aytar et al. “Playing hard exploration games by watching youtube”. In: Advances in Neural Information Processing Systems. 2018, pp. 2935-2945.

    Marc Bellemare et al. “Unifying count-based exploration and intrinsic motivation”. In: Advances in Neural Information Processing Systems. 2016, pp. 1471-1479.

    Sergey Levine et al. “End-to-end training of deep visuomotor policies”. In: The Journal of Machine Learning Research 17.1 (2016), pp. 1334-1373.

    Z. Li, U. Kalabic´, and T. Chu. “Safe Reinforcement Learning: Learning with Supervision Using a Constraint-Admissible Set”. In: 2018 Annual American Control Conference (ACC). June 2018, pp. 6390- 6395.

    Timothy P. Lillicrap et al. “Continuous control with deep reinforcement learning”. In: CoRR abs/1509.02971 (2015). arXiv: 1509.02971.

    Chung-Yen Lin, Liting Sun, and Masayoshi Tomizuka. “Robust principal component analysis for iterative learning control of precision motion systems with non-repetitive disturbances”. In: 2015 American Control Conference (ACC). IEEE. 2015, pp. 2819-2824.

    Kendall Lowrey et al. “Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control”. In: International Conference on Learning Representations. 2019.

  • Related Research Results (2)
  • Metrics
Share - Bookmark