Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs

By Weichao Mao, Kaiqing Zhang, Ruihao Zhu, David Simchi-Levi, Tamer Basar. 2021

49 citations recorded by the source corpus.

How researchers see this paper

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

1. Khimya Khetarpal
2. Matthew Riemer
3. Irina Rish
4. Doina Precup
5. Hongyuan Zha
6. Wenhao Li
7. Xiangfeng Wang
8. Bo Jin

Citations in the corpus

• Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “For example, another potentially interesting formulation is to assume arbitrary non-stationarity within a fixed variation budget as in (Mao et al., 2021).”
• Dealing with Non-Stationarity in MARL via Trust-Region Decomposition (2021, methodology): “Moreover, the changing opponents will significantly hinder the agent’s learning in MAS (Radanovic et al., 2019; Lee et al., 2020; Mao et al., 2021).”