Transcription of Asynchronous Methods for Deep Reinforcement …
{{id}} {{{paragraph}}}
Asynchronous Methods for deep Reinforcement LearningVolodymyr Puigdom nech P. DeepMind2 Montreal 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 instead of a GPU.
Asynchronous Methods for Deep Reinforcement Learning One way of propagating rewards faster is by using n-step returns (Watkins,1989;Peng & Williams,1996).
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}