Onno Eberhard
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
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.
Papers
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…