Reward-Mixing MDPs with a Few Latent Contexts are Learnable

5 October 2022

Papers citing "Reward-Mixing MDPs with a Few Latent Contexts are Learnable"

7 / 7 papers shown

Title
A Classification View on Meta Learning Bandits Mirco Mutti Jeongyeol Kwon Shie Mannor Aviv Tamar 18 0 0 06 Apr 2025
Test-Time Regret Minimization in Meta Reinforcement Learning Mirco Mutti Aviv Tamar 16 4 0 04 Jun 2024
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation Jeongyeol Kwon Shie Mannor C. Caramanis Yonathan Efroni OffRL 22 2 0 03 Jun 2024
Prospective Side Information for Latent MDPs Jeongyeol Kwon Yonathan Efroni Shie Mannor C. Caramanis 18 5 0 11 Oct 2023
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems Masatoshi Uehara Ayush Sekhari Jason D. Lee Nathan Kallus Wen Sun OffRL 47 31 0 24 Jun 2022
Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms Jeongyeol Kwon Yonathan Efroni C. Caramanis Shie Mannor AAML 35 6 0 30 Jan 2022
Learning mixtures of structured distributions over discrete domains Siu On Chan Ilias Diakonikolas Rocco A. Servedio Xiaorui Sun 51 83 0 02 Oct 2012