RLgraph: Flexible Computation Graphs for Deep Reinforcement Learning

10/21/2018
by   Michael Schaarschmidt, et al.
0

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 high performance RL computation graphs in both static graph and define-by-run paradigms. The resulting implementations yield high performance across different deep learning frameworks and distributed backends.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset