About
Discord Stateoftheart AI
GitHub

Publications

13

Cited by

246

Joshua Romoff

reinforcement learningdeep learning
Microsoft

United States

Papers and Citations

1 - 50
Hybrid reward architecture for reinforcement learning
2017
Tavian Barnes
Jeffrey Tsang
Harm van Seijen
+5
Cited by 155
Tarmac: Targeted multi-agent communication
2019
Joelle Pineau
Théophile Gervet
Dhruv Batra
+5
Cited by 80
Towards the systematic reporting of the energy and carbon footprints of machine learning
2020
Joelle Pineau
Jieru Hu
Dan Jurafsky
+4
Cited by 38
Randomized value functions via multiplicative normalizing flows
2020
Joelle Pineau
Pascal Vincent
Harsh Satija
+2
Cited by 19
Reward Estimation for Variance Reduction in Deep Reinforcement Learning
2018
Peter Henderson
Joelle Pineau
Joshua Romoff
+2
Cited by 17
Where did my optimum go?: An empirical analysis of gradient descent optimization in policy gradient methods
2018
Joshua Romoff
Joelle Pineau
Peter Henderson
Cited by 14
Multi-advisor reinforcement learning
2017
Harm van Seijen
Romain Laroche
Mehdi Fatemi
+1
Cited by 13
Separation of concerns in reinforcement learning
2016
Joshua Romoff
Harm van Seijen
Romain Laroche
+1
Cited by 10
Gossip-based actor-learner architectures for deep reinforcement learning
2019
Mahmoud (Mido) Assran
Michael Rabbat
Joshua Romoff
+2
Cited by 9
Separating value functions across time-scales
2019
Y Ollivier
Joelle Pineau
Emma Brunskill
+3
Cited by 4
Improving scalability of reinforcement learning by separation of concerns
2016
Harm van Seijen
Joshua Romoff
Mehdi Fatemi
+1
Cited by 3
Deep Reinforcement Learning for Navigation in AAA Video Games
2020
D Goumard
M Peter
Joshua Romoff
+1
Cited by 2
TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
2020
Peter Henderson
Joshua Romoff
Joelle Pineau
+4
Cited by 1
TDprop: Does Adaptive Optimization With Jacobi Preconditioning Help Temporal Difference Learning?
2021
Emmanuel Bengio
Peter Henderson
David Kanaa
+1
Cited by
About the attractor phenomenon in decomposed reinforcement learning
2018
Mehdi Fatemi
Harm van Seijen
Romain Laroche
+1
Cited by