Timezone: »

Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
Seungyul Han · Youngchul Sung

Tue Jul 20 05:25 AM -- 05:30 AM (PDT) @ None

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.

Author Information

Seungyul Han (KAIST)
Youngchul Sung (KAIST)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors