Kianté Brantley

Kianté Brantley is a Postdoctoral scholar at Cornell working with Thorsten Joachims. He completed his Ph.D. in computer science at the University of Maryland College Park (UMD) advised by Professor Hal Daumé III. Brantley designs algorithms that efficiently integrate domain knowledge into sequential decision-making problems. He is most excited about imitation learning and interactive learning—or, more broadly, settings that involve a feedback loop between a machine learning agent and the input the machine learning agent sees.

Before coming to UMD in 2016, Brantley attended the University of Maryland, Baltimore County where he earned his bachelor’s degree and master's degree (advised by Tim Oates) in computer science. He also worked as a data scientist for the U.S. Department of Defense from 2010 to 2017. In his free time, Brantley enjoys playing sports; his favorite sport at the moment is powerlifting. 

Brantley is a member of the UMD CLIP Lab, UMBC CORAL Lab and NYU CILVR lab.

I am on the job market looking for an academic or industry position!

Email  /  CV  /  Google Scholar  /  Semantic Scholar  /  Github  /  Twitter

profile photo
Research

I'm interested in designing algorithms that efficiently integrate domain knowledge into sequential decision making problems (e.g. reinforcement learning, imitation learning and structure prediction for natural language processing).

Publications
Adversarial Imitation Learning via Boosting
Jonathan Chang, Dhruv Sreenivas, Yingbing Huang, Kianté Brantley, Wen Sun
International Conference on Learning Representations (ICLR), 2024
[abstract]

Ranking with Long-Term Constraints
Kianté Brantley, Zhichong Fang, Sarah Dean, Thorsten Joachims,
Web Search and Data Mining (WSDM), 2024
[abstract]

Learning to Generate Better Than Your LLM
Jonathan Chang*, Kianté Brantley*, Rajkumar Ramamurthy, Dipendra Misra, Wen Sun,
arXiv, 2023
[abstract]

Interactive text generation
Felix Faltings, Michel Galley, Baolin Peng, Kianté Brantley, Weixin Cai, Yizhe Zhang, Jianfeng Gao, Bill Dolan,
Empirical Methods in Natural Language Processing (EMNLP), 2023
[abstract]

Is reinforcement learning (not) for natural language processing: Benchmarks, baselines, and building blocks for natural language policy optimization
Rajkumar Ramamurthy*, Prithviraj Ammanabrolu*, Kianté Brantley, Jack Hessel, Rafet Sifa, Christian Bauckhage, Hannaneh Hajishirzi, Yejin Choi,
International Conference on Learning Representations (ICLR), 2023 (Spotlight)
[abstract] [code] [blog]

lilGym: Natural Language Visual Reasoning with Reinforcement Learning
Anne Wu, Kianté Brantley, Noriyuki Kojima, Yoav Artzi,
Association for Computational Linguistics (ACL), 2022
[abstract] [code] [demo]

Proceedings of the First Workshop on Interactive Learning for Natural Language Processing
Kianté Brantley, Soham Dan, Iryna Gurevych, Ji-Ung Lee, Filip Radlinski, Hinrich Schütze, Edwin Simpson, Lili Yu,
Association for Computational Linguistics (ACL), 2021
[abstract]

Successor Feature Sets: Generalizing Successor Representations Across Policies
Kianté Brantley, Soroush Mehri, Geoffrey J. Gordon
Association for the Advancement of Artificial Intelligence (AAAI) , 2021
[abstract] [poster] [slides]

Constrained episodic reinforcement learning in concave-convex and knapsack settings
Kianté Brantley, Miroslav Dudik, Thodoris Lykouris, Sobhan Miryoosefi, Max Simchowitz, Aleksandrs Slivkins, Wen Sun
Conference on Neural Information Processing Systems (NeurIPS), 2020
[abstract] [code] [poster]

Active Imitation Learning with Noisy Guidance
Kianté Brantley, Amr Sharaf, Hal Daumé III
Association for Computational Linguistics (ACL), 2020
[abstract] [code] [poster] [slides] [video]

Disagreement-Regularized Imitation Learning
Kianté Brantley, Wen Sun, Mikael Henaff
International Conference on Learning Representations (ICLR), 2020 (Spotlight)
[abstract] [code] [poster] [slides] [video]

Non-monotonic sequential text generation
Sean Welleck, Kianté Brantley, Hal Daumé III, Kyunghyun Cho
International Conference on Machine Learning (ICML), 2019
[abstract] [code] [poster] [slides] [video]

Reinforcement Learning with Convex Constraints
Sobhan Miryoosefi*, Kianté Brantley*, Hal Daumé III, Miro Dudik, Robert Schapire
Conference on Neural Information Processing Systems (NeurIPS), 2019
[abstract] [code] [poster] [slides]

The umd neural machine translation systems at wmt17 bandit learning task
Amr Sharaf, Shi Feng, Khanh Nguyen, Kianté Brantley, Hal Daumé III
Second Conference on Machine Translation, 2017
[abstract] [poster]

BCAP: An Artificial Neural Network Pruning Technique to Reduce Overfitting
Kianté Brantley
University of Maryland, Baltimore County Master Thesis, 2016
[abstract] [slides]

LDAexplore: Visualizing topic models generated using latent dirichlet allocation
Ashwinkumar Ganesan, Kianté Brantley, Shimei Pan, Jian Chen
extvis Workshop - Intelligent User Interfaces (IUI), 2015
[abstract] [code] [slides]

Template from here