Timezone: »

 
Spotlight
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 Deep Reinforcement Learning 1 »

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.

Keywords: Reinforcement Learning and Planning · Deep RL
[ Paper ]

Author Information

Seungyul Han (KAIST)
Youngchul Sung (KAIST)

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

More from the Same Authors