2 papers
cs.AI2026
AutoGym: Blueprint-First Generation of Verifiable Agent Gyms
Aarati Andrea Noronha, Kavya Ravikumar, Carly Xiaoyu Lin
Training agents with reinforcement learning requires a gym, comprising a task, an executable environment in which the task can be attempted, and a verifier that reliably distinguis…
cs.RO2026
Interacting safely with cyclists using Hamilton-Jacobi reachability and reinforcement learning
Aarati Andrea Noronha, Jean Oh
In this paper, we present a framework for enabling autonomous vehicles to interact with cyclists in a manner that balances safety and optimality. The approach integrates Hamilton-J…