Jonathan D. Chang

I am a Senior Research Scientist at Databricks working as a technical lead for RL training for agentic systems. I was previously a Ph.D. student in the Computer Science department at Cornell University, advised by Wen Sun. Before Cornell, I recieved my bachelors in Computer Science and Applied Mathematics from Brown University in 2018, working with Stefanie Tellex and George Konidaris in the Humans to Robots (H2R) Laboratory.

CV / Email / Google Scholar / Github / LinkedIn

Research

I am interested in machine learning, specifically imitation learning and reinforcement learning, and its intersection with generative models. I am particularly interested in studying how to leverage expert demonstrations and learned feature representations for scalable, efficient reinforcement learning. Recently, I have been invested in investigating imitation learning and reinforcement learning for Large Language Models, improving sample efficiency, reducing reward hacking, and developing improved RLHF algorithms.

	KARL: Knowledge Agents via Reinforcement Learning Jonathan D. Chang, Andrew Drozdov, Shubham Toshniwal, Owen Oertell, Alexander Trott, Jacob Portes, Abhay Gupta, Pallavi Koppol, Ashutosh Baheti, Sean Kulinski, Ivan Zhou, Irene Dea, Krista Opsahl-Ong, Simon Favreau-Lessard, Sean Owen, Jose Javier Gonzalez Ortiz, Arnav Singhvi, Xabi Andrade, Cindy Wang, Kartik Sreenivasan, Sam Havens, Jialu Liu, Peyton DeNiro, Wen Sun, Michael Bendersky, Jonathan Frankle arXiv:2603.05218, 2026 arXiv
	LLMs Can Learn to Reason Via Off-Policy RL Daniel Ritter, Owen Oertell, Bradley Guo, Jonathan D. Chang, Kianté Brantley, Wen Sun arXiv:2602.19362, 2026 arXiv
	A State-of-the-Art SQL Reasoning Model using RLVR Alnur Ali, Ashutosh Baheti, Jonathan D. Chang, Ta-Chung Chi, Brandon Cui, Andrew Drozdov, Jonathan Frankle, Abhay Gupta, Pallavi Koppol, Sean Kulinski, Jonathan Li, Dipendra Misra, Krista Opsahl-Ong, Jose Javier Gonzalez Ortiz, Matei Zaharia, Yue Zhang arXiv:2509.21459, 2025 arXiv
	Simultaneous Multiobjective Alignment Across Verifiable and Non-verifiable Rewards Yiran Jenny Shen, Yu Xia, Jonathan D. Chang, Prithviraj Ammanabrolu Preprint, 2025
	Q♯: Provably Optimal Distributional RL for LLM Post-Training Jin Peng Zhou, Kaiwen Wang, Jonathan D. Chang, Zhaolin Gao, Nathan Kallus, Kilian Q. Weinberger, Kianté Brantley, Wen Sun NeurIPS, 2025
	Value-Guided Search for Efficient Chain-of-Thought Reasoning Kaiwen Wang, Jin Peng Zhou, Jonathan D. Chang, Zhaolin Gao, Nathan Kallus, Kianté Brantley, Wen Sun NeurIPS*, 2025
	Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF Zhaolin Gao, Wenhao Zhan, Jonathan D. Chang, Gokul Swamy, Kianté Brantley, Jason D. Lee, Wen Sun ICLR, 2025
	REBEL: Reinforcement Learning via Regressing Relative Rewards Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kianté Brantley, Thorsten Joachims, J. Andrew Bagnell, Jason D. Lee, Wen Sun NeurIPS, 2024
	RL for Consistency Models: Faster Reward Guided Text-to-Image Generation Owen Oertell, Jonathan D. Chang, Yiyi Zhang, Kianté Brantley, Wen Sun Reinforcement Learning Conference (RLC), 2024
	Critique-out-Loud Reward Models Zachary Ankner, Mansheej Paul, Brandon Cui, Jonathan D. Chang, Prithviraj Ammanabrolu arXiv:2408.11791, 2024 arXiv
	Dataset Reset Policy Optimization for RLHF Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Kianté Brantley, Dipendra Misra, Jason D. Lee, Wen Sun arXiv:2404.08495, 2024 arXiv
	TRIL: Transformers Reinforcement and Imitation Learning Algorithm Jonathan D. Chang, Kianté Brantley, Rajkumar Ramamurthy, Dipendra Misra, Wen Sun Repository, 2024 Github Developed, distributed research codebase for RL and IL algorithm development with large LLMs. Deepspeed, transformers, PEFT, and FSDP integration.
	Adversarial Imitation Learning via Boosting Jonathan D. Chang, Dhruv Sreenivas, Yingbing Huang, Kianté Brantley, Wen Sun ICLR, 2024 OpenReview
	Policy-Gradient Training of Language Models for Ranking Ge Gao, Jonathan D. Chang, Kianté Brantley, Claire Cardie, Thorsten Joachims FMDM@NeurIPS, 2023 arXiv
	Learning to Generate Better than Your LLM Jonathan D. Chang, Kianté Brantley, Rajkumar Ramamurthy, Dipendra Misra, Wen Sun arXiv:2306.11816, 2023 arXiv
	Learning Bellman Complete Representations for Offline Policy Evaluation Jonathan D. Chang, Kaiwen Wang, Nathan Kallus, Wen Sun ICML 2022 (Long Talk), 2022 code / arXiv Representation learning for Offline Policy Evaluation (OPE) guided by Bellman Completeness and coverage. BCRL achieves state-of-the-art evaluation on image based, continuous control tasks from Deepmind Control Suite.
	Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage Jonathan D. Chang, Masatoshi Uehara, Dhruv Sreenivas, Rahul Kidambi, Wen Sun NeurIPS 2021, 2021 code / arXiv Leveraging offline data with only partial coverage, MILO mitigates covariate shift in imitation learning.
	MobILE: Model-Based Imitation Learning from Observation Alone Rahul Kidambi, Jonathan D. Chang, Wen Sun NeurIPS 2021, 2021 arXiv We show that model-based imitation learning from observations (IfO) with strategic exploration can near-optimally solve IfO both in theory and in practice.

Preprints

Learning Deep Parameterized Skills from Demonstration for Re-targetable Visuomotor Control
Jonathan D. Chang*, Nishanth Kumar, Sean Hastings, Aaron Gokaslan, Diego Romeres, Devesh Jha, Daniel Nikovski, George Konidaris, Stefanie Tellex
arXiv

We introduce an end-to-end method for targetable visuomotor skills as a goal-parameterized neual network policy, resulting in successfully learning a mapping from target pixel coordinates to a robot policy.

Service

Reviewer: NeurIPS 2021, ICML 2022, ICLR 2022, NeurIPS 2022, NeurIPS 2023, ICML 2023, ICLR 2024, NeurIPS 2024, ICML 2024

Website template is from Jon Barron's website.