We introduce a new reliability infrastructure for file systems called I/O shepherding. I/O shepherding allows a file system developer to craft nuanced reliability policies to de...
Haryadi S. Gunawi, Vijayan Prabhakaran, Swetha Kri...
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
Embedded systems serve an emerging and diverse set of applications. As a result, more computational and storage capabilities are added to accommodate ever more demanding applicati...
Many current state-of-the-art planners rely on forward heuristic search. The success of such search typically depends on heuristic distance-to-the-goal estimates derived from the ...
Abstract. This paper proposes a novel approach to discover options in the form of conditionally terminating sequences, and shows how they can be integrated into reinforcement learn...