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

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 44
  • Download : 0
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.
Publisher
International Conference on Machine Learning (ICML)
Issue Date
2021-07
Language
English
Citation

International Conference on Machine Learning (ICML)

URI
http://hdl.handle.net/10203/286838
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0