Bio
I recently graduated with a PhD in Computer Science from Tufts University (May 2025). I worked in the The Assistive Agent Behavior and Learning Lab (AABL) under the supervision of Dr. Elaine Short. I graduated from Rugers University New Brunswick (2020) in the Honors Program with a BA in Cognitive Science and a minor in Computer Science. I am also a member of the Phi Beta Kappa Honors Society.
In Fall 2025, I will be starting a postdoctoral position at Brown University.Research Interests
My interests lie in people driven computer science. In other words, how to develop AI and robots that both help people and are inspired by people. To these ends, I am concerned with developing algorithms that allow robots to fluidly interact with and learn from humans.
Publications
- Towards Interpretable Foundation Models of Robot Behavior: A Task Specific Policy Generation Approach
Isaac Sheidlower, Reuben Aronson, Elaine Short
RLC 2024, Training Agents with Foundation Models (TAFM) Workshop, https://arxiv.org/abs/2407.08065 - Imagining In-distribution States: How Predictable Robot Behavior Can Enable User Control Over Learned Policies
Isaac Sheidlower, Emma Betherl, Douglas Lilly, Reuben Aronson, Elaine Short
IEEE RO-MAN 2024, Conference Paper, https://arxiv.org/pdf/2406.13711 - Online Behavior Modification for Expressive User Control of RL-Trained Robots
Isaac Sheidlower, Mavis Murdock, Emma Betherl, Reuben Aronson, Elaine Short
HRI 2024, Conference Paper, https://dl.acm.org/doi/abs/10.1145/3610977.3634947 - Modifying RL Policies with Imagined Actions: How Predictable Policies can Enable Users to Perform Novel Tasks
Isaac Sheidlower, Reuben Aronson, Elaine Short
AAAI Fall Symposium: AI-HRI, Short Contributions Paper, https://ai-hri.github.io/2023/papers/FSS-23_paper_9464_cr.pdf - Keeping Humans in the Loop: Teaching via Feedback in Continuous Action Space Environments
Isaac Sheidlower, Allison Moore, Elaine Short
IROS 2022, Conference Paper, https://ieeexplore.ieee.org/document/9982282 - Environment Guided Interactive Reinforcement Learning: Learning from Binary Feedback in High-Dimensional Robot Task Environments
Isaac Sheidlower, Allison Moore, Elaine Short
AAMAS 2022, Extended Abstract, https://dl.acm.org/doi/10.5555/3535850.3536090 - When Oracles Go Wrong: Using Preferences as a Means to Explore
Isaac Sheidlower, Elaine Short
HRI 2021, Late Breaking Report (LBR), https://dl.acm.org/doi/10.1145/3434074.3447189
Nominated for best LBR*
Get In Touch
Please email me with any inquiries. Thank you very much.