RLgraph: Modular Computation Graphs for Deep Reinforcement Learning
arXiv:1810.09028
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.
SysML 2019
References in corpus (7)
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- Simple random search provides a competitive approach to reinforcement learning
- Beyond Data and Model Parallelism for Deep Neural Networks
- TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
- LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations
- TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow