conftrace_

asynchronous method

4 papers

Explore in graph

Co-occurring keywords

asynchronous training (22) stochastic gradient descent (1091) deep reinforcement learning (903) error-runtime trade-off (1) neural network controller (20) proximal method (26) parallel training (37) neural network (6616) parallel actor-learner (2) continuous motor control (1)

Papers

Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD AISTATS 2018
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization NIPS 2017
Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods EMNLP 2017
Asynchronous Methods for Deep Reinforcement Learning ICML 2016