JQ
John Quan
cs.LGcs.AIstat.MLartificial intelligencecontinual learningdeep learningMachine LearningNeural Networks, Computerstability plasticitysynaptic consolidation
On Valency
published · living versionsW_mhugx9qb·v1 · currentpublished
Preprints & journals
16 papers in the corpus · 2015–2023Vision-Language Models as a Source of Rewards2312.09187v3 · Kate Baumli, Satinder Baveja, Feryal Behbahani et al.2023 · 4 citationsarXiv
The Phenomenon of Policy Churn2206.00730v3 · Tom Schaul, Andr'e Barreto, John Quan et al.2022 · 2 citationsarXiv
Podracer architectures for scalable Reinforcement Learning2104.06272v1 · Matteo Hessel, Manuel Kroiss, Aidan Clark et al.2021 · 8 citationsarXiv
The Value-Improvement Path: Towards Better Representations for Reinforcement Learning2006.02243v2 · Will Dabney, Andr'e Barreto, Mark Rowland et al.2020 · 20 citationsarXiv
General non-linear Bellman equations1907.03687v1 · Hado van Hasselt, John Quan, Matteo Hessel et al.2019 · 9 citationsarXiv
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement1901.10964v1 · Andr'e Barreto, Diana Borsa, John Quan et al.2019 · 79 citationsarXiv
Universal Successor Features Approximators1812.07626v1 · Diana Borsa, Andr'e Barreto, John Quan et al.2018 · 41 citationsarXiv
Observe and Look Further: Achieving Consistent Performance on Atari1805.11593v1 · Tobias Pohlen, Bilal Piot, Todd Hester et al.2018 · 80 citationsarXiv
Distributed Prioritized Experience Replay1803.00933v1 · Dan Horgan, John Quan, David Budden et al.2018 · 555 citationsarXiv
Unicorn: Continual Learning with a Universal, Off-policy Agent1802.08294v2 · Daniel J. Mankowitz, Augustin Z'idek, Andr'e Barreto et al.2018 · 35 citationsarXiv
Reply to Huszár: The elastic weight consolidation penalty is empirically valid.29463734 · Kirkpatrick, James, Pascanu, Razvan, Rabinowitz, Neil et al.2018 · 7 citationsProceedings of the National Academy of Sciences of the United States of America. 2018;115(11):E2498
StarCraft II: A New Challenge for Reinforcement Learning1708.04782v1 · Oriol Vinyals, Timo Ewalds, Sergey Bartunov et al.2017 · 678 citationsarXiv
Distral: Robust Multitask Reinforcement Learning1707.04175v1 · Yee Whye Teh, Victor Bapst, Wojciech Marian Czarnecki et al.2017 · 234 citationsarXiv
Deep Q-learning from Demonstrations1704.03732v4 · Todd Hester, Matej Vecerik, Olivier Pietquin et al.2017 · 1,021 citationsarXiv
Overcoming catastrophic forgetting in neural networks.28292907 · Kirkpatrick, James, Pascanu, Razvan, Rabinowitz, Neil et al.2018 · 7,771 citationsProceedings of the National Academy of Sciences of the United States of America. 2017;114(13):3521-3526
Prioritized Experience Replay1511.05952v4 · Tom Schaul, John Quan, Ioannis Antonoglou et al.2015 · 3,003 citationsarXivon Valency
Career total: 21 works. 16 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.