Zachary Serlin
Zachary Serlin works on verifiable multirobot coordination, formal methods, reinforcement learning and motion planning. His research uses capability temporal logic to express high-level team tasks. Serlin coauthored Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL. The team’s Def-MARL method uses a constrained optimization formulation for centralized training and distributed execution, with simulation tasks and quadcopter tests. Serlin coauthored Def-MARL with four others; the paper won RSS’s Outstanding Student Paper Award.
- Works
- 27
- Citations
- 339
- h-index
- 9
Publication numbers from OpenAlex, as of 14 October 2026.
Timeline
-
Research program
Specifications and robot teams
Zachary Serlin works on verifiable multirobot coordination, formal methods, reinforcement learning and motion planning. His research uses capability temporal logic to express high-level team tasks.
-
2025
Distributed safe control
Serlin coauthored Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL. The team’s Def-MARL method uses a constrained optimization formulation for centralized training and distributed execution, with simulation tasks and quadcopter tests.
-
2025
Shared student paper award
Serlin coauthored Def-MARL with four others; the paper won RSS’s Outstanding Student Paper Award.
Sources and credits
Photo: zacharyserlin.com; creator not stated. License: Not stated by source. Source: zacharyserlin.com. Cropped to a square and resized. Ask us to remove or replace this photo.