资源分类
》 资源 》论文》DeepMellow: Removing the Need for a Target Network in Deep Q-Learning

DeepMellow: Removing the Need for a Target Network in Deep Q-Learning

2019-10-08 | |  57 |   29 |   0
Abstract Deep Q-Network (DQN) is an algorithm that achieves human-level performance in complex domains like Atari games. One of the important elements of DQN is its use of a target network, which is necessary to stabilize learning. We argue that using a target network is incompatible with online reinforcement learning, and it is possible to achieve faster and more stable learning without a target network when we use Mellowmax, an alternative softmax operator. We derive novel properties of Mellowmax, and empirically show that the combination of DQN and Mellowmax, but without a target network, outperforms DQN with a target network

上一篇：Deep Active Learning with Adaptive Acquisition

下一篇：Discriminative Sample Generation for Deep Imbalanced Learning

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...