Peer Review Track Publications
Gymnasium: A Standard Interface for Reinforcement Learning Environments
Towers, Mark, Kwiatkowski, Ariel, Terry, J. K, Balis, John U and De Cola, Gianluca, Deleu, Tristan, Goulão, Manuel, Kallinteris, Andreas, Krimmel, Markus, KG, Arjun and others
Arxiv
|
2024
MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning
Felten, Florian, Ucak, Umut, Azmani, Hicham, Peng, Gao, Röpke, Willem, Baier, Hendrik, Mannion, Patrick, Roijers, Diederik M, Terry, J. K,, Talbi, El-Ghazali and others
Arxiv
|
2024
Minigrid & miniworld: Modular & customizable reinforcement learning environments for goal-oriented tasks
Chevalier-Boisvert, Maxime, Dai, Bolun, Towers, Mark, Perez-Vicente, Rodrigo, Willems, Lucas, Lahlou, Salem, Pal, Suman, Castro, Pablo Samuel, Terry, J. K.
NeurIPS 2024
|
2024
Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics
Tai, Jun Jet, Terry, J. K., Innocente, Mauro S., Brusey, James and Horri, Nadjim
arXiv
|
2022
Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments
Sullivan, Ryan, Terry, J. K., Black, Benjamin, Dickerson and John P.
ICML
|
2021
Revisiting parameter sharing in multi-agent deep reinforcement learning
Terry, J. K., Grammel, Nathaniel, Hari, Ananth, Santos, Luis, and Black, Benjamin
arXiv
|
2021
PettingZoo: Gym for multi-agent reinforcement learning
Terry, J. K., Grammel, Nathaniel , Hari, Ananth, Santos, Luis, and Black, Benjamin et. al.
NeurIPS 2021
|
2021
Accepted into AAMAS OptLearnMAS 2021 and NeurIPS Deep RL Workshops
Understanding generalization through visualizations
Huang, W. Ronny, Zeyad Emam, Micah Goldblum, Liam Fowl, Terry, J. K., Furong Huang, and Tom Goldstein
arXiv
|
2021
Accepted into NeurIPS ICBINB 2020 workshop, spotlight talk
Non-Peer Review Track Publications
Multi-Agent Deep Reinforcement Learning in 13 Lines of Code Using PettingZoo
Terry, J. K.
Towards Data Science
|
2021
Editors choice
Statistically Significant Stopping of Neural Network Training
Terry, J. K., Mario Jayakumar, and Kusal De Alwis.
arXiv
|
2021
Supersuit: Simple microwrappers for reinforcement learning environments
Terry, J. K., Black, B. and Hari, A.
arXiv
|
2020
Multiplayer support for the arcade learning environment
Terry, J. K.*, Benjamin Black*, and Luis Santos
arXiv
|
2020
Accepted into AAMAS OptLearnMAS 2021 Workshop , * Denotes equal contribution
Invited Talks
Modern Open Source Reinforcement Learning Tooling
Artificial Intelligence Finance Institute
|
February 2023
The Farama Foundation
Meta AI Research
|
January 2023
Umshini: A New Approach to RL Evaluation
Learning in Foundation Environments (LIFE)
|
August 2022
Umshini: A New Approach to RL Evaluation
HuggingFace
|
July 2022
Gym and the Future of Reinforcement Learning
Open Data Science Conference (ODSC)
|
April 2022
The Future of Gym and Reinforcement Learning
TalkRL Podcast
|
Dec 2021
Exploring Reward Surfaces in Deep Reinforcement Learning
K-KDD
|
Oct 2021
Gym and PettingZoo
ML Collective
|
August 2021
Monte Carlo Emergence Search and the Flocking Learning Environment
Army Research Laboratory
|
July 2021
PettingZoo
Toronto Synthetic Intelligence Forum
|
March 2021
Multi-Agent Reinforcement Learning: Systems for Evaluation and Relations to Complex Systems
UMD RLSS
|
January 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 (Semester Long Seminar)
Spring 2017
Other
Recipient of QinetiQ Fundamental Machine Learning Graduate Fellowship
Organizer of UMD Reinforcement Learning Seminar Series (RLSS)