Asynchronous Methods for Deep Reinforcement Learning
Asynchronous Methods for Deep Reinforcement LearningVolodymyr Puigdom nech P. DeepMind2Montreal Institute for Learning Algorithms (MILA), University of MontrealAbstractWeproposeaconceptuallysi mpleandlightweight framework for deep reinforce-ment Learning that uses Asynchronous gradientdescent for optimization of deep neural networkcontrollers. We present Asynchronous variants offour standard Reinforcement Learning algorithmsand show that parallel actor-learners have astabilizing effect on training allowing all fourmethods to successfully train neural best performing method, anasynchronous variant of actor-critic, surpassesthe current state-of-the-art on the Atari domainwhile training for half the time on a singlemulti-core CPU i
Asynchronous Methods for Deep Reinforcement Learning One way of propagating rewards faster is by using n-step returns (Watkins,1989;Peng & Williams,1996).
Download Asynchronous Methods for Deep Reinforcement Learning
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: