Kimang Khun

According to our database, Kimang Khun authored at least 6 papers between 2021 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

What is an Optimal Policy in Time-Average MDP?

Nicolas Gast, Bruno Gaujal, Kimang Khun

SIGMETRICS Perform. Evaluation Rev., September, 2023

Testing indexability and computing Whittle and Gittins index in subcubic time.

Nicolas Gast, Bruno Gaujal, Kimang Khun

Math. Methods Oper. Res., June, 2023

Algorithms for Markovian bandits: Indexability and Learning. (Des algorithmes pour les bandits markoviens: indexabilité et apprentissage).

Kimang Khun

PhD thesis, 2023

2022

Learning Algorithms for Markovian Bandits:\\Is Posterior Sampling more Scalable than Optimism?

Nicolas Gast, Bruno Gaujal, Kimang Khun

Trans. Mach. Learn. Res., 2022

Computing Whittle (and Gittins) Index in Subcubic Time.

Nicolas Gast, Bruno Gaujal, Kimang Khun

CoRR, 2022

2021

Reinforcement Learning for Markovian Bandits: Is Posterior Sampling more Scalable than Optimism?

Nicolas Gast, Bruno Gaujal, Kimang Khun

CoRR, 2021