papers AI Learner
The Github is limit! Click to go to the new site.

RLgraph: Modular Computation Graphs for Deep Reinforcement Learning

2019-02-28
Michael Schaarschmidt, Sven Mika, Kai Fricke, Eiko Yoneki

Abstract

Reinforcement learning (RL) tasks are challenging to implement, execute and test due to algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns. We argue for the separation of logical component composition, backend graph definition, and distributed execution. To this end, we introduce RLgraph, a library for designing and executing reinforcement learning tasks in both static graph and define-by-run paradigms. The resulting implementations are robust, incrementally testable, and yield high performance across different deep learning frameworks and distributed backends.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1810.09028

PDF

http://arxiv.org/pdf/1810.09028


Similar Posts

Comments