Corpus ID: 4570661

Recall Traces: Backtracking Models for Efficient Reinforcement Learning

@article{Goyal2019RecallTB,
  title={Recall Traces: Backtracking Models for Efficient Reinforcement Learning},
  author={Anirudh Goyal and Philemon Brakel and William Fedus and Soumye Singhal and Timothy P. Lillicrap and Sergey Levine and Hugo Larochelle and Yoshua Bengio},
  journal={ArXiv},
  year={2019},
  volume={abs/1804.00379}
}
  • Anirudh Goyal, Philemon Brakel, +5 authors Yoshua Bengio
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • In many environments only a tiny subset of all states yield high reward. [...] Key Method We can train a model which, starting from a high value state (or one that is estimated to have high value), predicts and sample for which the (state, action)-tuples may have led to that high value state.Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 25 CITATIONS

    InfoBot: Transfer and Exploration via the Information Bottleneck

    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND

    Empirical Policy Evaluation with Supergraphs

    VIEW 3 EXCERPTS
    CITES BACKGROUND

    Estimating Q(s, s') with Deep Deterministic Dynamics Gradients

    VIEW 1 EXCERPT
    CITES RESULTS

    Competitive Experience Replay

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Exploration via Hindsight Goal Generation

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    Generative Exploration and Exploitation

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 47 REFERENCES

    Automatic Goal Generation for Reinforcement Learning Agents

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Continuous control with deep reinforcement learning

    VIEW 4 EXCERPTS

    Deep Reinforcement Learning that Matters

    VIEW 1 EXCERPT

    Forward-Backward Reinforcement Learning

    VIEW 1 EXCERPT

    Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning

    VIEW 3 EXCERPTS

    Count-Based Exploration with Neural Density Models

    • A. PixelCNN Hyper-parameters
    • 2017
    VIEW 1 EXCERPT