Reinforcement Learning with Delayed, Composite, and Partially Anonymous Reward
收藏DataCite Commons2024-12-16 更新2025-04-16 收录
下载链接：
https://service.tib.eu/ldmservice/dataset/36ea7066-82a5-42c9-8be5-e3945f48a1e4
下载链接
链接失效反馈官方服务：
资源简介：
We investigate an infinite-horizon average reward Markov Decision Process (MDP) with delayed, composite, and partially anonymous reward feedback.
本文针对一类带有延迟、复合且部分匿名回报反馈的无限时域平均回报马尔可夫决策过程（Markov Decision Process，MDP）展开了研究。
提供机构：
TIB
创建时间：
2024-12-16
