Dylan Hirsch — accepted AI-conference papers

2026

Bellman Value Decomposition for Task Logic in Safe Optimal Control

William Sharpless, Oswin So, Dylan Hirsch, Sylvia Lee Herbert, Chuchu Fan

RSS 2026poster

Real-world tasks involve nuanced combinations of goal and safety specifications, which often directly compete. In high dimensions, the challenge is exacerbated: formal automata become cumbersome, and the combination of sparse rewards tends to require laborious tuning. In this work, we consider the s…

Cited by 0 Source ↗Scholar ↗

2026

Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations

William Sharpless, Dylan Hirsch, Sander Tonkens, Nikhil Uday Shinde, Sylvia Lee Herbert

ICLR 2026poster

Hard constraints in reinforcement learning (RL) often degrade policy performance. Lagrangian methods offer a way to blend objectives with constraints, but require intricate reward engineering and parameter tuning. In this work, we extend recent advances that connect Hamilton-Jacobi (HJ) equations wi…

Cited by 0 Source ↗Scholar ↗