NEWS
Free Institutional Consultancy Services
New Feature: Compare Your Institution with the Previous Year
Find a Professional: Explore Experts Across 197 Disciplines in 220 Countries!
Find a Professional
Print Your Certificate
New! Young University / Institution Rankings 2025
New! Art & Humanities Rankings 2025
New! Social Sciences and Humanities Rankings 2025
Highly Cited Researchers 2025
AD
Scientific Index 2025
Scientist Rankings
University Rankings
Subject Rankings
Country Rankings
login
Login
person_add
Register
insights
H-Index Rankings
insights
i10 Productivity Rankings
format_list_numbered
Citation Rankings
subject
University Subject Rankings
school
Young Universities
format_list_numbered
Top 100 Scientists
format_quote
Top 100 Institutions
format_quote
Compare & Choose
local_fire_department
Country Reports
person
Find a Professional
Joshua Romoff
McGill University - Montreal / Canada
Engineering & Technology / Computer Science
AD Scientific Index ID: 664601
Registration, Add Profile,
Premium Membership
Print Your Certificate
Ranking &
Analysis
Job
Experiences (0)
Education
Information (0)
Published Books (0)
Book Chapters (0)
Articles (0)
Presentations (0)
Lessons (0)
Projects (0)
Subject Leaders
Editorship, Referee &
Scientific Board (0 )
Patents /
Designs (0)
Academic Grants
& Awards (0)
Artistic
Activities (0)
Certificate / Course
/ Trainings (0)
Association &
Society Memberships (0)
Contact, Office
& Social Media
person_outline
Joshua Romoff's MOST POPULAR ARTICLES
1-)
Towards the systematic reporting of the energy and carbon footprints of machine learningP Henderson, J Hu, J Romoff, E Brunskill, D Jurafsky, J PineauThe Journal of Machine Learning Research 21 (1), 10039-10081, 20203322020
2-)
Tarmac: Targeted multi-agent communicationA Das, T Gervet, J Romoff, D Batra, D Parikh, M Rabbat, J PineauInternational Conference on Machine Learning, 1538-1546, 20193232019
3-)
Hybrid reward architecture for reinforcement learningH Van Seijen, M Fatemi, J Romoff, R Laroche, T Barnes, J TsangAdvances in Neural Information Processing Systems 30, 20172462017
4-)
Reward estimation for variance reduction in deep reinforcement learningJ Romoff, P Henderson, A Piché, V Francois-Lavet, J PineauConference on Robot Learning, 674-699, 2018512018
5-)
Where did my optimum go?: An empirical analysis of gradient descent optimization in policy gradient methodsP Henderson, J Romoff, J PineauarXiv preprint arXiv:1810.02525, 201850*2018
ARTICLES
Add your articles
We use cookies to personalize our website and offer you a better experience. If you accept cookies, we can offer you special services.
Cookie Policy
Accept