ICML 2021spotlight33 citations

Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration

Seungyul Han, Youngchul Sung

Abstract

In this paper, sample-aware policy entropy regularization is proposed to enhance the conventional policy entropy regularization for better exploration. Exploiting the sample distribution obtainable from the replay buffer, the proposed sample-aware entropy regularization maximizes the entropy of the weighted sum of the policy action distribution and the sample action distribution from the replay buffer for sample-efficient exploration. A practical algorithm named diversity actor-critic (DAC) is developed by applying policy iteration to the objective function with the proposed sample-aware entropy regularization. Numerical results show that DAC significantly outperforms existing recent algorithms for reinforcement learning.

BibTeX
@InProceedings{pmlr-v139-han21a,
  title = 	 {Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration},
  author =       {Han, Seungyul and Sung, Youngchul},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {4018--4029},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/han21a/han21a.pdf},
  url = 	 {https://proceedings.mlr.press/v139/han21a.html},
  abstract = 	 {In this paper, sample-aware policy entropy regularization is proposed to enhance the conventional policy entropy regularization for better exploration. Exploiting the sample distribution obtainable from the replay buffer, the proposed sample-aware entropy regularization maximizes the entropy of the weighted sum of the policy action distribution and the sample action distribution from the replay buffer for sample-efficient exploration. A practical algorithm named diversity actor-critic (DAC) is developed by applying policy iteration to the objective function with the proposed sample-aware entropy regularization. Numerical results show that DAC significantly outperforms existing recent algorithms for reinforcement learning.}
}
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration · ICML 2021