From the 1 of 9 linked papers with an AI index.
9 papers
Exact Decomposition of Adversarial Dual-Objective Value Functions, with Applications to Optimal Drug Dosing
Dylan Hirsch, William Sharpless, Sylvia Herbert
The paper proves that certain decompositions of dual‑objective value functions remain valid when an adversary is present, and demonstrates how this can be used to design optimal dr…
Bellman Value Decomposition for Task Logic in Safe Optimal Control
William Sharpless, Oswin So, Dylan Hirsch +2
Real-world tasks involve nuanced combinations of goal and safety specifications. In high dimensions, the challenge is exacerbated: formal automata become cumbersome, and the combin…
Value Functions for Temporal Logic: Optimal Policies and Safety Filters
Oswin So, William Sharpless, Sylvia Herbert +1
While Bellman equations for basic reach, avoid, and reach-avoid problems are well studied, the relationship between value optimality and policy optimality becomes subtle in the und…
Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations
William Sharpless, Dylan Hirsch, Sander Tonkens +2
Hard constraints in reinforcement learning (RL) often degrade policy performance. Lagrangian methods offer a way to blend objectives with constraints, but require intricate reward…
MADR: MPC-guided Adversarial DeepReach
Ryan Teoh, Sander Tonkens, William Sharpless +4
Hamilton-Jacobi (HJ) Reachability offers a framework for generating safe value functions and policies in the face of adversarial disturbance, but is limited by the curse of dimensi…
State-Augmented Linear Games with Antagonistic Error for High-Dimensional, Nonlinear Hamilton-Jacobi Reachability
Will Sharpless, Yat Tin Chow, Sylvia Herbert
Hamilton-Jacobi Reachability (HJR) is a popular method for analyzing the liveness and safety of a dynamical system with bounded control and disturbance. The corresponding HJ value…