2016 AsynchronousMethodsforDeepReinf

• (Mnih et al., 2016) ⇒ Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Tim Harley, Timothy P. Lillicrap, David Silver, and Koray Kavukcuoglu. (2016). “Asynchronous Methods for Deep Reinforcement Learning.” In: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48.

Subject Headings: A3C architecture, Distributed Actors, Deep RL.

Cited By

• http://scholar.google.com/scholar?q=%222016%22+Asynchronous+Methods+for+Deep+Reinforcement+Learning
• http://dl.acm.org/citation.cfm?id=3045390.3045594&preflayout=flat#citedby

Quotes

Abstract

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-core CPU instead of a GPU. Furthermore, we show that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task of navigating random 3D mazes using a visual input.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2016 AsynchronousMethodsforDeepReinf	Koray Kavukcuoglu Alex Graves Volodymyr Mnih David Silver Mehdi Mirza Tim Harley Adrià Puigdomènech Badia Timothy P. Lillicrap			Asynchronous Methods for Deep Reinforcement Learning						2016