Corpus ID: 55703664

Soft Actor-Critic Algorithms and Applications

@article{Haarnoja2018SoftAA,
  title={Soft Actor-Critic Algorithms and Applications},
  author={T. Haarnoja and Aurick Zhou and Kristian Hartikainen and G. Tucker and Sehoon Ha and J. Tan and V. Kumar and H. Zhu and A. Gupta and P. Abbeel and S. Levine},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.05905}
}
  • T. Haarnoja, Aurick Zhou, +8 authors S. Levine
  • Published 2018
  • Computer Science, Mathematics
  • ArXiv
  • Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample complexity and brittleness to hyperparameters. Both of these challenges limit the applicability of such methods to real-world domains. In this paper, we describe Soft Actor-Critic (SAC), our recently introduced off-policy actor-critic algorithm based on the… CONTINUE READING
    259 Citations

    Figures, Tables, and Topics from this paper.

    Deep RL With Information Constrained Policies: Generalization in Continuous Control
    • 2
    • Highly Influenced
    • PDF
    A Self-Tuning Actor-Critic Algorithm
    • 6
    • PDF
    Learning to Walk via Deep Reinforcement Learning
    • 79
    • PDF
    Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
    • 26
    • Highly Influenced
    • PDF
    Ready Policy One: World Building Through Active Learning
    • 6
    • PDF
    Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control
    Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
    • 21
    • PDF
    Towards Simplicity in Deep Reinforcement Learning: Streamlined Off-Policy Learning
    • 2
    • Highly Influenced
    Model-Augmented Actor-Critic: Backpropagating through Paths
    • 7
    • PDF

    References

    SHOWING 1-10 OF 46 REFERENCES
    Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
    • 997
    • PDF
    Continuous control with deep reinforcement learning
    • 3,793
    • Highly Influential
    • PDF
    Composable Deep Reinforcement Learning for Robotic Manipulation
    • 84
    • PDF
    Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
    • 209
    • PDF
    Benchmarking Deep Reinforcement Learning for Continuous Control
    • 895
    • PDF
    Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates
    • 598
    • PDF
    Reinforcement Learning with Deep Energy-Based Policies
    • 426
    • PDF
    End-to-End Training of Deep Visuomotor Policies
    • 1,875
    • PDF
    The Reactor: A Sample-Efficient Actor-Critic Architecture
    • 46
    • PDF