Joshua Romoff

Computer Science · Physical Sciences

9h-index801citations28works0.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(20), Artificial Intelligence in Games(5), Data Stream Mining Techniques(5), Adversarial Robustness in Machine Learning(4), Software Engineering Research(3)

Publications28 total

Assessing the Feasibility of Selective Instrumentation for Runtime Code Coverage in Large C++ Game Engines
ArXiv.org·2026Open Access
Assessing the Feasibility of Selective Instrumentation for Runtime Code Coverage in Large C++ Game Engines
arXiv (Cornell University)·2026Open Access
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play
2024
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play
arXiv (Cornell University)·2023Open Access
Improving Intrinsic Exploration by Creating Stationary Objectives
arXiv (Cornell University)·2023Open Access
Learning Computational Efficient Bots with Costly Features
2023· 2 citedOpen Access
Learning Computational Efficient Bots with Costly Features
arXiv (Cornell University)·2023Open Access
Direct Behavior Specification via Constrained Reinforcement Learning
arXiv (Cornell University)·2021· 4 citedOpen Access
Graph augmented Deep Reinforcement Learning in the GameRLand3D environment
arXiv (Cornell University)·2021· 2 citedOpen Access
Graph augmented Deep Reinforcement Learning in the GameRLand3D environment
HAL (Le Centre pour la Communication Scientifique Directe)·2021Open Access
Deep Reinforcement Learning for Navigation in AAA Video Games
2021· 6 citedOpen Access
TDprop: Does Adaptive Optimization With Jacobi Preconditioning Help Temporal Difference Learning?
2021
TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
arXiv (Cornell University)·2020· 2 citedOpen Access
Towards the Systematic Reporting of the Energy and Carbon Footprints of\n Machine Learning
arXiv (Cornell University)·2020· 303 citedOpen Access
Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning
arXiv (Cornell University)·2020· 174 citedOpen Access
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
arXiv (Cornell University)·2019· 19 citedOpen Access
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
arXiv (Cornell University)·2019· 7 citedOpen Access
Separating value functions across time-scales
arXiv (Cornell University)·2019· 4 citedOpen Access
TarMAC: Targeted Multi-Agent Communication
arXiv (Cornell University)·2018· 26 citedOpen Access
Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
arXiv (Cornell University)·2018· 16 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Joëlle Pineau(12), Peter Henderson(8), Harm van Seijen(5), Mehdi Fatemi(5), Romain Laroche(5), Abdelaziz Touati(4), Philippe Marcotte(4), Emma Brunskill(3), Michael Rabbat(3), Maxim Peter(3), Pierre‐Luc Bacon(3), Dan Jurafsky(2), Mahmoud Assran(2), Nicolas Ballas(2), Alexandre Piché(2), Vincent François-Lavet(2), David Kanaa(2), Emmanuel Bengio(2), Anthony Kobanda(2), C. A. Valliappan(2)