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

    Figures, Tables, and Topics from this paper.

    Learning to Walk via Deep Reinforcement Learning
    • 66
    • PDF
    End-to-End Robotic Reinforcement Learning without Reward Engineering
    • 55
    • PDF
    Diagnosing Bottlenecks in Deep Q-learning Algorithms
    • 36
    • PDF
    Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
    • 50
    • PDF
    Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
    • 36
    • PDF
    A Theory of Regularized Markov Decision Processes
    • 57
    • PDF
    Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
    • 18
    • Highly Influenced
    • PDF
    Towards Characterizing Divergence in Deep Q-Learning
    • 34
    • PDF
    Dynamics-Aware Unsupervised Discovery of Skills
    • 34
    • PDF
    Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
    • 17
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 46 REFERENCES
    Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
    • 867
    • PDF
    Continuous control with deep reinforcement learning
    • 3,529
    • Highly Influential
    • PDF
    Adam: A Method for Stochastic Optimization
    • 49,762
    • PDF
    Human-level control through deep reinforcement learning
    • 9,811
    • PDF
    Asynchronous Methods for Deep Reinforcement Learning
    • 3,302
    • Highly Influential
    • PDF
    End-to-End Training of Deep Visuomotor Policies
    • 1,799
    • PDF
    Benchmarking Deep Reinforcement Learning for Continuous Control
    • 852
    • PDF
    Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates
    • 560
    • PDF
    Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
    • 207
    • PDF
    Reinforcement Learning with Deep Energy-Based Policies
    • 405
    • PDF