Yike Zhao
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1Stats ML×1
Frequent co-authors
Research Timeline
2026
Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
This paper theoretically justifies the strong performance of linear recurrent neural networks as memory units in partially observable reinforcement learning by constructing specific linear filters that serve as sufficient statistics for optimal policy learning.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIstat.MLRecentMay 29, 2026
Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
Yike Zhao, Onno Eberhard, Malek Khammassi, Ali H. Sayed +1 more
This paper theoretically justifies the strong performance of linear recurrent neural networks as memory units in partially observable reinforcement learning by constructing specific linear filters tha…
View →