Metatrace Actor-Critic: Online Step-size Tuning by Meta-gradient Descent
for Reinforcement Learning Control

Metatrace Actor-Critic: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control

10 May 2018

Baoxiang Wang

Matthew E. Taylor

Papers citing "Metatrace Actor-Critic: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control"

9 / 9 papers shown

Title
TIDBD: Adapting Temporal-difference Step-sizes Through Stochastic Meta-descent Alex Kearney Vivek Veeriah Jaden B. Travnik R. Sutton P. Pilarski 17 16 0 10 Apr 2018
Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents Marlos C. Machado Marc G. Bellemare Erik Talvitie J. Veness Matthew J. Hausknecht Michael Bowling 58 549 0 18 Sep 2017
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning Stefan Elfwing E. Uchibe Kenji Doya 53 1,690 0 10 Feb 2017
Asynchronous Methods for Deep Reinforcement Learning Volodymyr Mnih Adria Puigdomenech Badia M. Berk Mirza Alex Graves Timothy Lillicrap Tim Harley David Silver Koray Kavukcuoglu 159 8,805 0 04 Feb 2016
Deep Reinforcement Learning with Double Q-learning H. V. Hasselt A. Guez David Silver OffRL 125 7,590 0 22 Sep 2015
High-Dimensional Continuous Control Using Generalized Advantage Estimation John Schulman Philipp Moritz Sergey Levine Michael I. Jordan Pieter Abbeel OffRL 38 3,368 0 08 Jun 2015
Adam: A Method for Stochastic Optimization Diederik P. Kingma Jimmy Ba ODL 678 149,474 0 22 Dec 2014
Normalized Online Learning Stéphane Ross Paul Mineiro John Langford 86 69 0 09 Aug 2014
Playing Atari with Deep Reinforcement Learning Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra Martin Riedmiller 89 12,163 0 19 Dec 2013

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.