Posterior sampling with delayed feedback for reinforcement learning with linear function approximation
Recent studies in reinforcement learning (RL) have made significant progress by leveraging
function approximation to alleviate the sample complexity hurdle for better performance.
Despite the success, existing provably efficient algorithms typically rely on the accessibility
of immediate feedback upon taking actions. The failure to account for the impact of delay in
observations can significantly degrade the performance of real-world systems due to the
regret blow-up. In this work, we tackle the challenge of delayed feedback in RL with linear …
function approximation to alleviate the sample complexity hurdle for better performance.
Despite the success, existing provably efficient algorithms typically rely on the accessibility
of immediate feedback upon taking actions. The failure to account for the impact of delay in
observations can significantly degrade the performance of real-world systems due to the
regret blow-up. In this work, we tackle the challenge of delayed feedback in RL with linear …
Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
N Lijing Kuang, M Yin, M Wang, YX Wang… - arXiv e …, 2023 - ui.adsabs.harvard.edu
Recent studies in reinforcement learning (RL) have made significant progress by leveraging
function approximation to alleviate the sample complexity hurdle for better performance.
Despite the success, existing provably efficient algorithms typically rely on the accessibility
of immediate feedback upon taking actions. The failure to account for the impact of delay in
observations can significantly degrade the performance of real-world systems due to the
regret blow-up. In this work, we tackle the challenge of delayed feedback in RL with linear …
function approximation to alleviate the sample complexity hurdle for better performance.
Despite the success, existing provably efficient algorithms typically rely on the accessibility
of immediate feedback upon taking actions. The failure to account for the impact of delay in
observations can significantly degrade the performance of real-world systems due to the
regret blow-up. In this work, we tackle the challenge of delayed feedback in RL with linear …
以上显示的是最相近的搜索结果。 查看全部搜索结果