Corpus ID: 218630003

Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning

@article{Lee2020ContextawareDM,
  title={Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning},
  author={Kimin Lee and Younggyo Seo and Seunghyun Lee and Honglak Lee and Jinwoo Shin},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.06800}
}
  • Kimin Lee, Younggyo Seo, +2 authors Jinwoo Shin
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a challenging task. To tackle this problem, we decompose the task of learning a global dynamics model into two stages: (a) learning a context latent vector that captures the local dynamics, then (b) predicting the next state conditioned on it. In order to encode… CONTINUE READING

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES

    Environment Probing Interaction Policies

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    MuJoCo: A physics engine for model-based control

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL