A novel DDPG method with prioritized experience replay

By Yuenan Hou, Lifeng Liu, Qing Wei, Xudong Xu, Chunlin Chen. 2017

247 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sergey Levine
2. Aviral Kumar
3. Abhishek Gupta
4. Chelsea Finn
5. Pieter Abbeel
6. Shixiang Shane Gu
7. Keith W. Ross
8. Che Wang

In Computer Networks and Communications

1. Aviral Kumar
2. Sergey Levine
3. Keith W. Ross
4. Abhishek Gupta

Citations in the corpus

• DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction (2020, methodology): “Prioritized sampling has been used previously in ADP methods to instead prioritize transitions with higher Bellman error (Schaul et al., 2015; Hessel et al., 2018; Hou et al., 2017; Horgan et al., 2018).”
• Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past (2019, methodology): “PER has also been successfully applied to other algorithms such as DDPG [15] and can be implemented in a distributed manner [14].”