Brett Barkley

I am a PhD student at the University of Texas at Austin advised by David Fridovich-Keil.

I was previously employed by the Johns Hopkins Applied Physics Laboratory, where I worked on AI-based autonomy for aerospace systems.

I have an MS in Aerospace Engineering from the University of Maryland where I was a research assistant under Prof. Derek Paley and member of the Collective Dynamics and Control Laboratory (CDCL). My area of specialization was flight dynamics, stability, and control and my thesis proposed a scalable cooperative autonomy framework for multi-agent aerial reconnaissance.

CV  /  Email  /  Google Scholar  /  LinkedIn

Research Interest

I study how to make synthetic data more reliable and effective for scaling AI training pipelines. My work challenges the assumption that even well-structured synthetic data is always beneficial, showing that, without careful integration and diagnostics, it can degrade performance or distort learning dynamics. I develop methods for structured data augmentation, failure analysis, and algorithmic repair to make synthetic data more trustworthy. Recent projects include empirical studies exposing structural flaws in model-based RL pipelines built on synthetic rollouts, time-symmetric data augmentation in sequential decision-making problems, and ongoing development of diagnostic tools for out-of-distribution detection using diffusion models, aimed at identifying when synthetic data distributions diverge from trusted real-world contexts.

News

• Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning was accepted to ICML. (May 2025)
• An Investigation of Time Reversal Symmetry in Reinforcement Learning was accepted to L4DC. (April 2024)
• Our work on AI for air-to-air combat was recently featured in The New Yorker. (Jan 2022)
• I was promoted to sub and full scale red autonomy lead for DARPA's Air Combat Evolution! (Sept 2020)
• Our work on AI for simulated 1v1 dogfighting as part of the DARPA AlphaDogfightTrials program was recently featured in the Economist, Fortune, Forbes, and Popular Mechanics. (Aug 2020)
• I joined the Intelligent Combat Platforms group at the Johns Hopkins Applied Physics Laboratory. (Apr 2019)

We identify when, where, and why synthetic rollouts destabilize MBPO, and propose simple remediations that allow it to perform exceptionally well in environments where it previously could not improve beyond a random policy.

We introduce a diffusion-based OOD detection method using score curvature to measure typicality, enabling fast, reliable detection across vision and RL datasets.

We show that synthetic rollouts in model-based RL can actually harm performance, identifying fundamental instabilities in Dyna-style methods.

We explore the role of time symmetry in RL algorithms and propose new augmentation strategies that exploit this structure.

Design and source code adapted from here