Skip to main content
Publications Talks Teaching

Publications

Asterisk (*) indicates equal contribution.

Meta-World+: An Improved, Standardized, RL Benchmark.
R. McLean, E. Chatzaroulas, L. McCutcheon, F. Röder, T. Yu, Z. He, KR Zentner, R. Julian, J. K. Terry, I. Woungang, N. Farsad, P. Samuel Castro. NeurIPS 2025.
Multi-Task Reinforcement Learning Enables Parameter Scaling.
R. McLean, E. Chatzaroulas, J. K. Terry, I. Woungang, N. Farsad, P. Samuel Castro. Reinforcement Learning Conference 2025.
Outstanding Paper Award on Scientific Understanding in Reinforcement Learning
A2Perf: Real-World Autonomous Agents Benchmark.
I. Uchendu, J. Jabbour, K. Van den Berghe, J. Runevic, M. Stewart, J. Ma, S. Krishnan, I. Gur, A. Huang, C. Bishop, P. Bailey, W. Jiang, E. M Songhori, S. Guadarrama, J. Tan, J. K. Terry, A. Faust, V. Janapa Reddi. arXiv 2025.
Gymnasium: A Standard Interface for Reinforcement Learning Environments.
M. Towers*, A. Kwiatkowski*, J. K. Terry*, J. U. Balis, G. De Cola, T. Deleu, M. Goulão, A. Kallinteris, M. Krimmel, Markus, A. KG, and others. NeurIPS 2024.
Spotlight paper
MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning.
F. Felten, U. Ucak, H. Azmani, G. Peng, W. Röpke, H. Baier, P. Mannion, D. M. Roijers, J. K. Terry, E.-G. Talbi, and others. arXiv 2024.
Minigrid & miniworld: Modular & customizable reinforcement learning environments for goal-oriented tasks.
M. Chevalier-Boisvert, B. Dai, M. Towers, R. Perez-Vicente, L. Willems, S. Lahlou, S. Pal, P. S. Castro, J. K. Terry. NeurIPS 2024.
Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics.
J. J. Tai, J. K. Terry, M. S. Innocente, J. Brusey, N. Horri. arXiv 2022.
Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments.
R. Sullivan, J. K. Terry, B. Black, J. P. Dickerson. ICML 2021.
Revisiting parameter sharing in multi-agent deep reinforcement learning.
J. K. Terry, N. Grammel, A. Hari, L. Santos, B. Black. arXiv 2021.
PettingZoo: Gym for multi-agent reinforcement learning.
J. K. Terry, B. Black, N. Grammel, M. Jayakumar, A. Hari, R. Sullivan, L. Santos, C. Dieffendahl, C. Horsch, R. Perez-Vicente, N. Williams, Y. Lokesh, P. Ravi. NeurIPS 2021.
Accepted into AAMAS OptLearnMAS 2021 and NeurIPS Deep RL Workshops
Understanding generalization through visualizations.
W. R. Huang, Z. Emam, M. Goldblum, L. Fowl, J. K. Terry, F. Huang, and T. Goldstein. arXiv 2021.
Accepted into NeurIPS ICBINB 2020 workshop, spotlight talk
Statistically Significant Stopping of Neural Network Training.
J. K. Terry, M. Jayakumar, K. De Alwis. arXiv 2021.
Supersuit: Simple microwrappers for reinforcement learning environments.
J. K. Terry, B. Black, A. Hari. arXiv 2020.
Multiplayer support for the arcade learning environment.
J. K. Terry*, B. Black*, L. Santos. arXiv 2020.
Accepted into AAMAS OptLearnMAS 2021 Workshop

Talks

Gym and the Future of Reinforcement Learning
Open Data Science Conference (ODSC), April 2022
Exploring Reward Surfaces in Deep Reinforcement Learning
K-KDD, Oct 2021
PettingZoo
Toronto Synthetic Intelligence Forum, March 2021

Teaching

Introduction to Artificial Intelligence (Undergraduate) | CMSC421
Spring 2019
Deep Learning (Graduate) | CMSC828L
Fall 2018
* At the time of writing, this course number now corresponds to a different course
Applied Machine Learning (Undergraduate) | PHYS476
Spring 2018
* Invited by department to create and teach course; it has now become permanent and is offered annually
Machine Learning for Physicists
Spring 2017
* Semester long seminar